© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89601
    Prev
    Next
    INDEX
    Explanations

    ABDL

    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
    0
    0.75
    ible
    0.72
    in
    0.71
    ud
    0.71
    í
    0.70
    ди
    0.69
    ά
    0.69
    ی
    0.68
    ہ
    0.68
    پ
    0.68
    POSITIVE LOGITS
     dotycz
    0.86
    tól
    0.71
    ferencia
    0.64
    กรา
    0.64
    ميم
    0.63
    كين
    0.63
    DbType
    0.60
    ポジション
    0.60
     Manche
    0.60
     Elektrokh
    0.59
    Activations Density 0.001%

    No Known Activations