© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260086
    Prev
    Next
    INDEX
    Explanations

    distances and durations

    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_22_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
     অসু
    0.37
    скоп
    0.37
    分布
    0.35
    哟
    0.34
    SENSOR
    0.34
    이버
    0.34
     আচরণ
    0.34
     ocular
    0.33
    Readers
    0.33
    뿜
    0.33
    POSITIVE LOGITS
     selepas
    0.43
     nakon
    0.42
     Nakon
    0.40
     just
    0.40
    rem
    0.39
     relatively
    0.39
    尧
    0.39
     setelah
    0.39
    katapos
    0.39
     Ba
    0.38
    Activations Density 0.000%

    No Known Activations