© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5406
    Prev
    Next
    INDEX
    Explanations

    code-like text or hyphenated phrases

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    writeFieldEnd
    -0.62
     defaultstate
    -0.51
     endblock
    -0.44
    setLayoutManager
    -0.44
    cience
    -0.43
    NSIndexPath
    -0.43
     por
    -0.42
     combineReducers
    -0.41
    itename
    -0.40
    initro
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.90
    ^(@)
    0.76
    허
    0.71
    èlement
    0.71
    AsUp
    0.70
     poffible
    0.66
    contentLoaded
    0.66
    thâu
    0.65
    <bos>
    0.65
    StoreMessageInfo
    0.63
    Activations Density 0.586%

    No Known Activations