© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11309
    Prev
    Next
    INDEX
    Explanations

    information and answers

    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_13_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
    kin
    0.41
    koord
    0.41
    ra
    0.41
     Perp
    0.40
     Malaysia
    0.39
     Kuala
    0.39
     Fukuoka
    0.38
     h
    0.38
     Penang
    0.38
     Freiburg
    0.38
    POSITIVE LOGITS
     figlia
    0.43
    <0x0D>
    0.41
    🩺
    0.40
    信息
    0.40
    נת
    0.40
     tiled
    0.40
    用户信息
    0.39
    از
    0.39
     ദ
    0.38
     信息
    0.38
    Activations Density 0.202%

    No Known Activations