© 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. 42364
    Prev
    Next
    INDEX
    Explanations

    pom.xml files, security threats

    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
    ри
    0.69
    od
    0.67
    ش
    0.66
    )
    0.65
    ry
    0.64
    س
    0.64
    ע
    0.63
    ور
    0.63
    '
    0.63
    $),
    0.60
    POSITIVE LOGITS
    на
    0.97
    െയുള്ള
    0.66
    ب
    0.63
    実績
    0.61
    بك
    0.60
     académicos
    0.60
    ene
    0.58
     ढंग
    0.57
     intérieur
    0.56
    人用
    0.56
    Activations Density 0.000%

    No Known Activations