© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8006
    Prev
    Next
    INDEX
    Explanations

    words in forms or tables related to names

    oai_token-act-pair · gemini-2.0-flash

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ویکی‌پدیا
    -0.47
     localVar
    -0.47
    脚注の使い方
    -0.44
     فريبيس
    -0.43
     either
    -0.42
    >*/
    -0.41
    agliari
    -0.41
     ‘
    -0.40
    ătoare
    -0.39
    гинал
    -0.39
    POSITIVE LOGITS
    TestingModule
    0.80
    basicConfig
    0.71
    enumi
    0.68
    twimg
    0.64
     الاطلاع
    0.63
    createCanvas
    0.62
    \{\\
    0.62
    ]--;
    0.60
    ]^{-
    0.60
    GEBURTSDATUM
    0.60
    Activations Density 1.403%

    No Known Activations