© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41520
    Prev
    Next
    INDEX
    Explanations

    styrofoam or polystyrene

    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_3_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
    ли
    0.93
    ल
    0.91
    の
    0.89
     pierwszy
    0.88
    ת
    0.88
    ри
    0.82
    在
    0.81
     primeiro
    0.80
    は
    0.80
    هم
    0.80
    POSITIVE LOGITS
    r
    0.97
    I
    0.95
    .
    0.86
    ut
    0.82
    ts
    0.71
    ast
    0.70
    roll
    0.70
    ada
    0.69
    o
    0.69
    ach
    0.68
    Activations Density 0.015%

    No Known Activations