© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204425
    Prev
    Next
    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     ۱۴
    0.57
     seventy
    0.54
    ″
    0.49
     ۱۰
    0.49
     twelve
    0.47
     fourteen
    0.45
     ১০
    0.44
     eighty
    0.44
     ninety
    0.44
     Seventy
    0.43
    POSITIVE LOGITS
    oporosis
    0.39
    HN
    0.38
    കളുടെ
    0.37
    phobic
    0.37
    置
    0.37
    вшиеся
    0.36
    чности
    0.35
    োনো
    0.35
    ኞ
    0.35
    гия
    0.34
    Activations Density 0.001%

    No Known Activations