© 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. 134825
    Prev
    Next
    INDEX
    Explanations

    level of experience

    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
    which
    0.96
    که
    0.89
     that
    0.88
    5
    0.88
    that
    0.83
     of
    0.82
    ai
    0.79
    ac
    0.79
    ।
    0.79
    what
    0.78
    POSITIVE LOGITS
     jeopardize
    0.82
     ș
    0.82
     fertilized
    0.81
     nutr
    0.77
     be
    0.77
     ها
    0.77
     ผม
    0.76
     fiberglass
    0.76
     bygg
    0.76
     b
    0.75
    Activations Density 0.000%

    No Known Activations