© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50684
    Prev
    Next
    INDEX
    Explanations

    `::` Haskell type signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #!/
    0.18
    ある
    0.17
    瓠
    0.17
    h
    0.16
     =
    0.16
     was
    0.16
     kasut
    0.15
     Norway
    0.15
     Accessories
    0.15
     Automatic
    0.15
    POSITIVE LOGITS
    са
    0.25
    ي
    0.22
    ياب
    0.20
    м
    0.20
    то
    0.20
    ’
    0.20
    és
    0.19
    '
    0.18
    acent
    0.18
    يش
    0.17
    Activations Density 0.014%

    No Known Activations