© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193478
    Prev
    Next
    INDEX
    Explanations

    game settings

    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_4_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
    us
    1.07
    at
    1.06
    ro
    1.05
    re
    1.02
    ک
    1.00
    ry
    0.96
    ী
    0.95
    on
    0.95
    یه
    0.94
    and
    0.93
    POSITIVE LOGITS
    好吃
    0.80
    市
    0.76
     delante
    0.75
     zag
    0.73
    ઓ
    0.69
    ás
    0.69
     a
    0.68
     ét
    0.68
     заяви
    0.68
     gegeven
    0.68
    Activations Density 0.000%

    No Known Activations