© 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. 15030
    Prev
    Next
    INDEX
    Explanations

    months of the year

    oai_token-act-pair · gemini-2.0-flash

    dates and time-related tokens

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

    November

    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
    TagMode
    -0.67
    +:+
    -0.65
    midler
    -0.60
    WebServlet
    -0.55
     يتيمه
    -0.54
     sẻ
    -0.54
    clusal
    -0.54
    cycline
    -0.52
    anthin
    -0.49
     prochaines
    -0.47
    POSITIVE LOGITS
    StoreMessageInfo
    0.67
    ContentAsync
    0.63
    Predecesor
    0.56
     ProtoMessage
    0.53
     EdgeInsets
    0.52
    deci
    0.52
    LLocation
    0.50
     للمعارف
    0.50
    RunAsync
    0.49
    --*/
    0.47
    Activations Density 0.320%

    No Known Activations