© 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. 126379
    Prev
    Next
    INDEX
    Explanations

    json keys

    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
    า
    0.96
     a
    0.87
    ing
    0.81
    가
    0.80
    스
    0.78
    apa
    0.75
    he
    0.74
    ியா
    0.74
    ı
    0.73
    点
    0.70
    POSITIVE LOGITS
    ي
    0.65
    isierte
    0.62
    ゾート
    0.59
    !!!");
    0.59
    mitglied
    0.58
    isches
    0.57
    0.56
    )");
    0.55
     oliva
    0.55
     accentuated
    0.55
    Activations Density 0.010%

    No Known Activations