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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    words that begin a caption or step of a procedure

    oai_token-act-pair · gemini-2.0-flash

    Structured information/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ContentAsync
    -0.76
    parsedMessage
    -0.65
    EndContext
    -0.62
    postIndex
    -0.61
    Искәрмәләр
    -0.59
    帖最后由
    -0.59
    ungalows
    -0.58
    ceptre
    -0.58
    fieldname
    -0.58
    kampf
    -0.57
    POSITIVE LOGITS
    <bos>
    1.36
    hl
    0.54
    by
    0.53
    ead
    0.47
     >::
    0.47
     onOptions
    0.47
    '
    0.46
     समीक्षाओं
    0.45
    dy
    0.45
    for
    0.45
    Activations Density 3.774%

    No Known Activations