© 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. 38909
    Prev
    Next
    INDEX
    Explanations

    database connection

    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
    el
    0.95
    ed
    0.75
    \
    0.71
    al
    0.69
    an
    0.68
    ل
    0.68
    I
    0.67
    alimentation
    0.67
    ル
    0.65
    qualiter
    0.65
    POSITIVE LOGITS
    that
    0.63
     that
    0.62
    t
    0.59
     שה
    0.56
    vann
    0.55
    ↵
    0.53
    ።
    0.52
     que
    0.52
     THAT
    0.52
     deinen
    0.52
    Activations Density 0.002%

    No Known Activations