© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially those relating to real estate and architecture

    oai_token-act-pair · gemini-2.0-flash

    words related to storytelling

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

    Number of bedrooms

    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
    Negative Logits
     виправивши
    -0.51
     twain
    -0.51
     calitate
    -0.48
     faſt
    -0.47
     navigable
    -0.46
    RTCK
    -0.46
    ืน
    -0.46
     tropics
    -0.46
    TypeService
    -0.45
    inigungs
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.79
     Stories
    0.65
     stories
    0.65
     story
    0.65
     Story
    0.64
     AspNetCore
    0.64
    jenih
    0.63
    tanleria
    0.60
     STORY
    0.59
    STORY
    0.59
    Activations Density 0.701%

    No Known Activations