© 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. 167212
    Prev
    Next
    INDEX
    Explanations

    ; list separators

    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
    :"))
    0.45
    酽
    0.42
     totiž
    0.38
    {(
    0.37
    :""
    0.36
    訣
    0.36
    ką
    0.36
    vDash
    0.35
    ittha
    0.35
    %{
    0.34
    POSITIVE LOGITS
    ;
    1.04
    ；
    0.90
     ;
    0.82
    ؛
    0.75
     ؛
    0.71
    ;
    0.69
    $;
    0.68
    .;
    0.65
    ፤
    0.64
    ;/
    0.63
    Activations Density 0.115%

    No Known Activations