© 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. 3834
    Prev
    Next
    INDEX
    Explanations

    the word "fill" or "stat" in code or configuration files

    oai_token-act-pair · gemini-2.0-flash

    fill

    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
     HasFactory
    -0.71
     TextInputType
    -0.66
     dAtA
    -0.66
    bcryptjs
    -0.64
    Xna
    -0.64
    Pyx
    -0.63
    ыгана
    -0.63
    GHIJKLM
    -0.62
    urlpatterns
    -0.60
    IMPORTED
    -0.59
    POSITIVE LOGITS
    ViewStyle
    0.62
    HTTPClient
    0.57
     Drapeau
    0.55
    parsedMessage
    0.53
     priorité
    0.52
    gawai
    0.52
     debout
    0.51
    omentos
    0.50
    ParallelGroup
    0.50
     kív
    0.50
    Activations Density 0.306%

    No Known Activations