© 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. 142222
    Prev
    Next
    INDEX
    Explanations

    web browser

    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
    ambuk
    0.38
    hythmic
    0.37
    tod
    0.35
    SpawnEntry
    0.34
     Transfers
    0.34
    %=
    0.34
     atleta
    0.34
    ശി
    0.34
    ỷ
    0.34
    igned
    0.33
    POSITIVE LOGITS
     web
    0.59
    웹
    0.57
     웹
    0.54
     ওয়েব
    0.54
     वेब
    0.53
     ویب
    0.53
     веб
    0.50
     WebView
    0.49
     webs
    0.48
     इंटरनेट
    0.48
    Activations Density 0.008%

    No Known Activations