© 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. 193587
    Prev
    Next
    INDEX
    Explanations

    0%; provided

    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
    ী
    0.53
     Interment
    0.49
    ill
    0.48
     Khim
    0.47
    Vit
    0.46
    '?
    0.46
    Complete
    0.44
     DRS
    0.43
    า
    0.43
     ні
    0.43
    POSITIVE LOGITS
    gada
    0.55
     técnicos
    0.49
    es
    0.49
    يلا
    0.47
    صف
    0.47
    ceiling
    0.46
     ثقاف
    0.46
    렇게
    0.46
    فيد
    0.46
    섹
    0.46
    Activations Density 0.000%

    No Known Activations