© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157937
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ли
    1.22
    ن
    1.19
    이나
    1.11
    ۰
    0.98
    ل
    0.95
     писа
    0.95
    {//
    0.93
     proliferating
    0.91
     گویا
    0.90
     repercussions
    0.89
    POSITIVE LOGITS
    an
    1.57
    i
    1.41
    ان
    1.28
    at
    1.20
     for
    1.19
    d
    1.17
    as
    1.16
    c
    1.16
    time
    1.14
    S
    1.09
    Activations Density 0.000%

    No Known Activations