© 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. 927
    Prev
    Next
    INDEX
    Explanations

    words prefixed with "con" or "so", possibly in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    Mixed language, special characters

    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
     fieldNum
    -0.84
    __":
    -0.71
     CreateTagHelper
    -0.71
    PreExecute
    -0.69
    )");
    -0.63
    ValueGenerated
    -0.63
    fjspx
    -0.61
    ;");
    -0.57
    }');
    -0.57
     commercially
    -0.56
    POSITIVE LOGITS
    ագրություններ
    0.49
    avl
    0.47
    stdc
    0.46
    Примітки
    0.45
    общение
    0.45
    caud
    0.43
     poitrine
    0.41
    ⓧ
    0.41
     esternos
    0.41
     שוליים
    0.41
    Activations Density 0.091%

    No Known Activations