© 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. 41836
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ন
    0.72
    н
    0.67
    <h2>
    0.66
    奖
    0.63
    νες
    0.63
    ال
    0.62
    ’”
    0.62
    ن
    0.61
    ت
    0.61
    <h1>
    0.61
    POSITIVE LOGITS
    っており
    0.58
     prototypical
    0.55
    тся
    0.52
    xhr
    0.51
    actionMode
    0.51
     computationally
    0.51
     पहाड़ी
    0.50
    ною
    0.50
     perplex
    0.50
    funktionen
    0.49
    Activations Density 0.000%

    No Known Activations