© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88944
    Prev
    Next
    INDEX
    Explanations

    Alba, Kumar, require

    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_23_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
    itoare
    0.48
     कैल्शियम
    0.48
    ę
    0.48
    ло
    0.46
    .~
    0.46
    ण्यासाठी
    0.46
    пора
    0.45
     ეს
    0.45
    Algun
    0.45
     மற்ற
    0.44
    POSITIVE LOGITS
    ซ์
    0.52
     امتحان
    0.44
     Freed
    0.44
     Cher
    0.43
    u
    0.43
    uot
    0.42
     Wool
    0.41
     Paramount
    0.41
     parade
    0.41
    車種
    0.41
    Activations Density 0.000%

    No Known Activations