© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15293
    Prev
    Next
    INDEX
    Explanations

    technical language discussing houses and/or how they are built, along with words that describe soil, building materials or the perimeters of structures.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "foundation"

    np_token-act-pair-logits · gpt-4o-mini

    foundation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    şekkür
    -0.56
    سته
    -0.54
    bierz
    -0.54
    ReusableCell
    -0.53
     Librarian
    -0.50
    ží
    -0.48
    Demografie
    -0.47
    saurus
    -0.47
     BoxFit
    -0.47
    MockBean
    -0.46
    POSITIVE LOGITS
     foundation
    1.15
     foundations
    1.04
    foundation
    0.94
     Foundation
    0.89
    Foundation
    0.89
     FOUNDATION
    0.88
     Foundations
    0.79
    Foundations
    0.76
     septic
    0.73
     фунда
    0.66
    Activations Density 2.541%

    No Known Activations