© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12326
    Prev
    Next
    INDEX
    Explanations

    fade out or outro

    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_13_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
     능력
    0.18
     本当
    0.16
    <unused693>
    0.16
     হয়ে
    0.16
    }$;
    0.16
    }$,
    0.16
     चाहती
    0.15
     মনের
    0.15
     ソフト
    0.15
     イベント
    0.15
    POSITIVE LOGITS
    cca
    0.14
    \(
    0.14
       
    0.13
     name
    0.13
    ל
    0.13
     predicate
    0.13
    医院
    0.13
    ناف
    0.12
    /
    0.12
    ület
    0.12
    Activations Density 0.002%

    No Known Activations