© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40599
    Prev
    Next
    INDEX
    Explanations

    zip archive processing and gender descriptors

    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
    Negative Logits
    س
    0.98
    ن
    0.81
    с
    0.79
    ン
    0.73
    گنڈ
    0.70
    धपुर
    0.69
    ন
    0.68
    త్మిక
    0.65
    ス
    0.64
    nda
    0.63
    POSITIVE LOGITS
    -
    0.76
    .
    0.70
     zip
    0.67
    ين
    0.65
    ות
    0.61
    야
    0.61
    了一
    0.60
    ก
    0.59
    ឹម
    0.59
     conventional
    0.58
    Activations Density 0.020%

    No Known Activations