© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32673
    Prev
    Next
    INDEX
    Explanations

    jiu jitsu

    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_7_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
    ，
    0.86
    ".
    0.80
    Configure
    0.77
    Do
    0.76
     participe
    0.73
    Maintain
    0.73
    in
    0.72
    EN
    0.71
    >();
    0.70
    Durante
    0.70
    POSITIVE LOGITS
    ad
    1.07
    ación
    0.95
     for
    0.94
    yn
    0.88
    ول
    0.84
    ul
    0.80
    ud
    0.77
     was
    0.77
    ide
    0.76
    ow
    0.76
    Activations Density 0.000%

    No Known Activations