© 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. 201316
    Prev
    Next
    INDEX
    Explanations

    say "Twitch"

    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
    ယ
    0.44
    foils
    0.38
     가
    0.38
     ਦੇ
    0.37
    َد
    0.37
    cot
    0.37
    toBottomOf
    0.37
    loh
    0.36
    VideoButton
    0.36
    ویان
    0.36
    POSITIVE LOGITS
     Kings
    0.41
    Kings
    0.41
     tenant
    0.41
     fore
    0.40
     Богу
    0.40
     briefing
    0.39
     मुख्‍य
    0.38
    屯
    0.38
     three
    0.38
     echo
    0.38
    Activations Density 0.002%

    No Known Activations