© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103409
    Prev
    Next
    INDEX
    Explanations

    file imports and declarations

    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_16_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
     ту
    0.49
    atic
    0.47
    м
    0.47
    ated
    0.46
    🫐
    0.45
     tái
    0.44
    ượu
    0.44
     chua
    0.44
    tio
    0.43
    か
    0.43
    POSITIVE LOGITS
    EN
    0.44
    ｸ
    0.44
    ኺ
    0.43
    WITH
    0.43
    ುಕ
    0.43
    गर्
    0.43
     besoins
    0.42
    ConnectionString
    0.42
     branch
    0.42
    errors
    0.41
    Activations Density 0.000%

    No Known Activations