© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116670
    Prev
    Next
    INDEX
    Explanations

    .

    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_27_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
    epochs
    0.37
    equations
    0.36
    CP
    0.34
    منابع
    0.34
    genomes
    0.33
    UpSync
    0.33
    никами
    0.33
    ਥ
    0.32
    ૂર્વ
    0.32
    뎁
    0.31
    POSITIVE LOGITS
     Matt
    0.33
     особенностей
    0.32
     অন্যদিকে
    0.32
     признаки
    0.32
    刚
    0.32
     Kerr
    0.31
     handbook
    0.31
     Fewer
    0.31
    꼈
    0.31
     friendliness
    0.31
    Activations Density 0.025%

    No Known Activations