© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111711
    Prev
    Next
    INDEX
    Explanations

    HRIS, CRM, ERP integrations

    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_2_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
     in
    1.61
     در
    1.32
    在
    1.28
    ও
    1.01
    도
    0.96
    もら
    0.95
    dari
    0.91
    in
    0.91
     firma
    0.90
    z
    0.88
    POSITIVE LOGITS
    리
    1.54
    ны
    1.28
    લ
    1.28
    ர
    1.18
    ла
    1.09
    ות
    1.07
    க்க
    1.05
    ру
    1.05
    ם
    1.05
    乆
    1.05
    Activations Density 0.000%

    No Known Activations