© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12793
    Prev
    Next
    INDEX
    Explanations

    various names of function routines, names of items in a calendar, and the Korean word for year

    oai_token-act-pair · gemini-2.0-flash

    년

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    룡
    -0.85
    벡터
    -0.77
    많
    -0.73
    벽
    -0.69
    높
    -0.69
    되지
    -0.66
     것이다
    -0.66
    륜
    -0.66
    뜩
    -0.65
    죽
    -0.62
    POSITIVE LOGITS
    ⓧ
    0.88
    حوالہ
    0.86
    MigrationBuilder
    0.81
    SaveChangesAsync
    0.79
    enumii
    0.79
    ngdoc
    0.78
    findpost
    0.75
    httphttps
    0.74
    sizeCache
    0.73
    __':
    0.71
    Activations Density 2.277%

    No Known Activations