© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61646
    Prev
    Next
    INDEX
    Explanations

    overall [number, performance, pattern, trust, control, purpose, operating]

    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_11_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
     or
    0.63
     donn
    0.57
     renom
    0.57
     battlefield
    0.53
     dram
    0.53
     ordnance
    0.53
     McCoy
    0.52
     ó
    0.52
     реши
    0.52
     мой
    0.52
    POSITIVE LOGITS
    ना
    0.63
    ar
    0.63
    Ф
    0.60
     Szk
    0.59
    Plants
    0.58
    -"+
    0.58
    CHARGE
    0.58
     Workshops
    0.58
    Stack
    0.57
    COMM
    0.57
    Activations Density 0.004%

    No Known Activations