© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202756
    Prev
    Next
    INDEX
    Explanations

    telegram bot handlers

    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_12_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
     الف
    0.55
    ،
    0.55
    ，
    0.53
     અભ
    0.51
     in
    0.50
    با
    0.50
    ”،
    0.49
     بالم
    0.49
     अगला
    0.48
    Faz
    0.47
    POSITIVE LOGITS
     bruke
    0.61
     jego
    0.57
    iftoire
    0.57
     powinien
    0.57
     सिंगापुर
    0.55
    圩
    0.55
     tiende
    0.54
     سائٹ
    0.54
     njegov
    0.54
    Singapore
    0.53
    Activations Density 0.001%

    No Known Activations