© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199790
    Prev
    Next
    INDEX
    Explanations

    view followed by nouns or descriptions

    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_9_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
    س
    1.34
    સ
    0.96
    า
    0.89
    ল
    0.82
    ない
    0.80
    对
    0.79
    ス
    0.77
    ট
    0.77
    ם
    0.76
     juices
    0.75
    POSITIVE LOGITS
    t
    0.87
    ين
    0.67
     mange
    0.64
    cheng
    0.64
    يك
    0.64
    ί
    0.61
     canad
    0.61
    ce
    0.60
    vrez
    0.60
     calent
    0.60
    Activations Density 0.003%

    No Known Activations