© 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. 41036
    Prev
    Next
    INDEX
    Explanations

    Anna Karenina or ANSWER KEY

    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
    िक
    0.48
    生まれた
    0.46
    nol
    0.45
    بد
    0.45
    injured
    0.44
    Australian
    0.44
    Figure
    0.44
    ,}
    0.44
    និង
    0.43
    Thickness
    0.43
    POSITIVE LOGITS
    сор
    0.46
    ｺ
    0.46
    ఆర్
    0.45
     filosóf
    0.45
     cognit
    0.43
    జీ
    0.43
     gente
    0.42
     delà
    0.41
     lest
    0.41
    క్షి
    0.41
    Activations Density 0.000%

    No Known Activations