© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38470
    Prev
    Next
    INDEX
    Explanations

    DOTmed, Doraville, dot art, DomCrawler

    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_3_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
    ;
    1.08
    :
    1.06
    ir
    1.00
    a
    0.84
     }
    0.83
    ור
    0.83
    या
    0.82
     $
    0.81
    ?
    0.81
    at
    0.80
    POSITIVE LOGITS
    سين
    0.77
    ксана
    0.76
    makeConstraints
    0.72
    biss
    0.67
    ᐟ
    0.64
    ющимся
    0.63
     പോലെ
    0.63
    كان
    0.62
    اريخ
    0.62
    AccessToken
    0.62
    Activations Density 0.003%

    No Known Activations