© 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. 231526
    Prev
    Next
    INDEX
    Explanations

    names associated with people, places, and specific entities

    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
    ت
    1.33
    y
    1.23
     I
    1.07
    t
    1.00
    س
    1.00
    ed
    0.92
    us
    0.91
    dons
    0.85
    ،
    0.84
    f
    0.78
    POSITIVE LOGITS
    ER
    0.85
    "#
    0.84
    "
    0.82
    nder
    0.79
    يل
    0.75
    キャラクター
    0.74
     supermerc
    0.73
     teeming
    0.73
    га
    0.72
    ká
    0.72
    Activations Density 0.001%

    No Known Activations