© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50863
    Prev
    Next
    INDEX
    Explanations

    completions or com

    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_10_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
    ك
    0.75
    ট
    0.70
    国的
    0.67
    ılan
    0.66
    什么
    0.65
     identifying
    0.65
     journalists
    0.64
     indications
    0.64
    枴
    0.64
     IE
    0.63
    POSITIVE LOGITS
    ал
    0.73
     કેટલી
    0.71
    uk
    0.70
    или
    0.68
    ус
    0.67
    шуу
    0.66
    я
    0.64
    ун
    0.63
    de
    0.62
    <0x80>
    0.61
    Activations Density 0.001%

    No Known Activations