© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79358
    Prev
    Next
    INDEX
    Explanations

    `lib/`, `unset`, `__pycache__`

    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_31_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
    filtration
    0.38
    䒱
    0.37
     Justine
    0.35
     मात्र
    0.35
     kilometres
    0.34
    Dollars
    0.34
     hectares
    0.34
     estaciones
    0.34
    
    0.34
    istes
    0.33
    POSITIVE LOGITS
     conflit
    0.41
     bson
    0.37
     hint
    0.37
     useless
    0.37
    ្សា
    0.37
    ndo
    0.36
     inactivity
    0.35
    힌
    0.35
     declare
    0.35
     ember
    0.35
    Activations Density 0.000%

    No Known Activations