© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9646
    Prev
    Next
    INDEX
    Explanations

    double check

    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_13_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
    v
    0.50
    Tour
    0.44
    તિ
    0.44
     üy
    0.44
    tj
    0.44
    rivi
    0.44
    veter
    0.44
    Association
    0.43
    𝒅
    0.43
    あらゆる
    0.43
    POSITIVE LOGITS
    on
    0.45
    os
    0.43
    owej
    0.42
     propellant
    0.42
     scrotum
    0.40
    oy
    0.40
    าย
    0.39
    ך
    0.39
    ારા
    0.38
     accentuated
    0.38
    Activations Density 0.123%

    No Known Activations