© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205063
    Prev
    Next
    INDEX
    Explanations

    Start/begin (languages)

    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_56_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
    ់
    0.39
    kenn
    0.38
    ರೇ
    0.38
    [
    0.37
     acts
    0.37
     wholesale
    0.37
    __[
    0.37
    Division
    0.37
    ()['
    0.36
     hurtful
    0.36
    POSITIVE LOGITS
     시작
    0.50
     beginnen
    0.47
    開始
    0.46
     iniziare
    0.46
     cominc
    0.46
     begin
    0.45
     começando
    0.45
     começar
    0.45
     شروع
    0.45
     begyn
    0.44
    Activations Density 0.000%

    No Known Activations