© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13994
    Prev
    Next
    INDEX
    Explanations

    stats having to do with football games

    oai_token-act-pair · gemini-2.0-flash

    yards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    脚注の使い方
    -0.94
    __":
    -0.84
    expandindo
    -0.84
    abestanden
    -0.82
    DockStyle
    -0.81
     onPostExecute
    -0.81
     propOrder
    -0.81
    __':
    -0.79
    __':
    -0.79
    saraba
    -0.79
    POSITIVE LOGITS
     interne
    0.52
    acka
    0.47
    ToUser
    0.44
    ınca
    0.43
     getResource
    0.43
     seni
    0.43
     indicato
    0.41
    celli
    0.40
    ρή
    0.40
     hại
    0.40
    Activations Density 1.379%

    No Known Activations