© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192763
    Prev
    Next
    INDEX
    Explanations

    margin, persones, parlen

    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_4_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
     be
    0.66
    ﺩ
    0.60
    IAN
    0.58
    L
    0.58
    ASE
    0.57
    ли
    0.56
    R
    0.54
    T
    0.54
    SER
    0.53
    مي
    0.51
    POSITIVE LOGITS
    ir
    0.88
    a
    0.73
    एं
    0.62
     individualism
    0.61
     numériques
    0.61
    ul
    0.59
     взя
    0.59
     घेतली
    0.58
    uée
    0.57
    on
    0.57
    Activations Density 0.000%

    No Known Activations