© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41069
    Prev
    Next
    INDEX
    Explanations

    accounting for

    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_11_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
    es
    0.88
    d
    0.81
    f
    0.80
    st
    0.77
    v
    0.74
    h
    0.74
    in
    0.70
    は
    0.69
    ve
    0.67
    a
    0.67
    POSITIVE LOGITS
    на
    0.71
     другу
    0.64
    йт
    0.62
    йд
    0.61
    ње
    0.58
     GATT
    0.58
    િત
    0.57
    дио
    0.56
    йда
    0.55
    ὼ
    0.55
    Activations Density 0.002%

    No Known Activations