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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 970
    Prev
    Next
    INDEX
    Explanations

    a mix of terms about music, politics and race.

    oai_token-act-pair · gemini-2.0-flash

    media and politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     []).
    -0.69
    awtextra
    -0.59
    CodedInputStream
    -0.59
    []);
    -0.55
     nakalista
    -0.53
    ()");
    -0.52
    leyebilirsiniz
    -0.52
    +#+
    -0.52
     NUKAT
    -0.50
     دیکھیے
    -0.50
    POSITIVE LOGITS
    typeorm
    0.55
    sizeCache
    0.52
    pacho
    0.51
    érature
    0.51
    awaiter
    0.50
    dormit
    0.48
    הערות
    0.47
    InputBorder
    0.46
    Autoritní
    0.46
    Handlung
    0.46
    Activations Density 2.946%

    No Known Activations