© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236134
    Prev
    Next
    INDEX
    Explanations

    flatten each

    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_25_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
    );
    0.24
    ;
    0.20
     when
    0.20
    ,
    0.18
     When
    0.17
    ”,
    0.17
    時刻
    0.17
     confortable
    0.17
     زمن
    0.17
    ];
    0.17
    POSITIVE LOGITS
    筅
    0.23
     నిషే
    0.23
    뉩
    0.21
    MENU
    0.21
    뉜
    0.21
     чого
    0.21
    主义
    0.21
    🍴
    0.21
     دھو
    0.20
     następnie
    0.20
    Activations Density 0.002%

    No Known Activations