© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19020
    Prev
    Next
    INDEX
    Explanations

    signal

    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_15_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
    app
    0.58
    edly
    0.58
    features
    0.54
    dv
    0.53
    type
    0.52
    models
    0.52
    _),
    0.52
    igno
    0.52
    chip
    0.52
    extern
    0.51
    POSITIVE LOGITS
     ваша
    0.60
     shea
    0.58
     изо
    0.57
     eyeshadow
    0.57
     artesan
    0.57
     ശക്ത
    0.55
     insufficiency
    0.55
     प्रमाणित
    0.55
     сертифика
    0.55
     z
    0.54
    Activations Density 0.010%

    No Known Activations