© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13730
    Prev
    Next
    INDEX
    Explanations

    tokens associated with writing, media, teaching and reporting.

    oai_token-act-pair · gemini-2.0-flash

    words related to passages or sections of text

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

    text block

    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
     EconPapers
    -0.66
     ProtoMessage
    -0.63
    SharedCtor
    -0.61
     CreateTagHelper
    -0.57
     Meksiku
    -0.56
     propOrder
    -0.54
    tanleria
    -0.51
    стота
    -0.51
     newBuilder
    -0.50
    TintMode
    -0.49
    POSITIVE LOGITS
     passage
    0.82
    passage
    0.74
     sentence
    0.68
    Passage
    0.62
     page
    0.61
     pass
    0.60
     Passage
    0.59
     chapter
    0.59
     paragraph
    0.59
     passages
    0.59
    Activations Density 5.052%

    No Known Activations