© 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. 33894
    Prev
    Next
    INDEX
    Explanations

    on average

    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
    ता
    0.66
     opér
    0.66
    ح
    0.66
    ח
    0.63
    って
    0.63
    N
    0.62
    O
    0.60
     înv
    0.59
    き
    0.58
    نڈ
    0.57
    POSITIVE LOGITS
    k
    1.00
     for
    0.86
    3
    0.81
    n
    0.77
    ;
    0.73
     H
    0.71
    0.71
    ри
    0.66
    sat
    0.65
    kult
    0.64
    Activations Density 0.013%

    No Known Activations