© 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. 41851
    Prev
    Next
    INDEX
    Explanations

    active directory or duty

    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
    ע
    1.05
    ج
    0.82
    데이
    0.76
    ه
    0.75
    ש
    0.75
    י
    0.73
    いますが
    0.72
    ي
    0.72
    μα
    0.72
    활동
    0.71
    POSITIVE LOGITS
    ne
    0.76
    on
    0.72
    S
    0.70
    n
    0.70
     و
    0.69
    ita
    0.69
    _
    0.68
    en
    0.68
    os
    0.68
    -
    0.68
    Activations Density 0.014%

    No Known Activations