© 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. 90471
    Prev
    Next
    INDEX
    Explanations

    extraterrestrial intelligence projects

    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
    a
    0.94
    ه
    0.93
    ה
    0.92
    ہ
    0.85
    e
    0.85
    t
    0.82
    d
    0.79
    е
    0.73
    ի
    0.72
    ee
    0.69
    POSITIVE LOGITS
    ول
    0.67
    ুল
    0.63
     Ци
    0.62
     Информация
    0.62
     Зна
    0.61
     तरह
    0.60
    ER
    0.60
    to
    0.59
    芢
    0.59
    翛
    0.58
    Activations Density 0.001%

    No Known Activations