© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137719
    Prev
    Next
    INDEX
    Explanations

    Hitchhiker's Guide

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ilmiş
    0.38
     města
    0.38
    manı
    0.38
    ilmesi
    0.37
    撃
    0.37
    غراف
    0.37
     mieście
    0.37
     города
    0.36
     graphically
    0.36
    द्दीन
    0.36
    POSITIVE LOGITS
    પી
    0.44
    Iw
    0.40
    PI
    0.40
    朗
    0.40
    MK
    0.39
     પી
    0.39
    ലി
    0.39
     Pik
    0.38
    ኺ
    0.38
    ivanje
    0.37
    Activations Density 0.011%

    No Known Activations