Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10199
    Prev
    Next
    INDEX
    Explanations

    numeric codes

    oai_token-act-pair · gemini-2.0-flash

    HTTP status codes and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     response
    -0.52
     Response
    -0.49
     responding
    -0.47
     responses
    -0.46
    Responding
    -0.45
    respon
    -0.44
     poch
    -0.44
    Response
    -0.43
     responded
    -0.43
    respond
    -0.42
    POSITIVE LOGITS
    StructEnd
    0.88
     utafitiHapana
    0.82
     ExecuteAsync
    0.78
     initComponents
    0.76
    دانشنامهٔ
    0.75
     jScrollPane
    0.73
    Rhestr
    0.73
    ViewFeatures
    0.73
     محفوظة
    0.72
    NameInMap
    0.71
    Activations Density 0.512%

    No Known Activations