© 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. 7534
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially numbers split across tokens and ranges including "h".

    oai_token-act-pair · gemini-2.0-flash

    foreign language tokens or programming terms

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

    numbers and foreign languages

    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
    StructEnd
    -0.81
     يتيمه
    -0.81
    ^(@)
    -0.80
    ագրություններ
    -0.75
     كومونز
    -0.75
    OGND
    -0.74
    mergeFrom
    -0.74
    eseorang
    -0.71
     >=",
    -0.71
    ItemBackground
    -0.71
    POSITIVE LOGITS
    ばかり
    0.42
     femininos
    0.40
    %
    0.40
    MongoClient
    0.37
    gs
    0.36
     preguntó
    0.35
     tradicionais
    0.35
     değiştir
    0.35
    CreateModel
    0.35
     poteva
    0.34
    Activations Density 5.678%

    No Known Activations