© 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. 129498
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    0
    1.88
    ;
    1.33
    x
    1.27
    א
    1.20
    %
    1.17
    ח
    1.16
    ب
    1.16
    ING
    1.14
    ０
    1.11
    ’
    1.09
    POSITIVE LOGITS
    速度
    0.94
     boulevard
    0.92
     caldera
    0.88
     howling
    0.86
    ración
    0.86
     bibliothèque
    0.84
    ологі
    0.84
    策
    0.83
     dinâmica
    0.82
    社
    0.82
    Activations Density 0.003%

    No Known Activations