© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134721
    Prev
    Next
    INDEX
    Explanations

    Gilded Cage

    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_6_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
     နောက်
    0.93
    とされる
    0.92
    ческих
    0.91
    грева
    0.91
     Виктор
    0.89
    약을
    0.88
    ᱖
    0.88
    क्रोस
    0.85
    ման
    0.85
     seguinte
    0.83
    POSITIVE LOGITS
     in
    1.40
    ing
    1.20
    ,
    1.18
     to
    1.17
    ’
    1.16
     (
    1.13
     on
    1.13
     album
    1.12
    ];
    1.09
     envi
    1.09
    Activations Density 0.000%

    No Known Activations