© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50511
    Prev
    Next
    INDEX
    Explanations

    *

    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_55_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
     OR
    0.74
     N
    0.67
    n
    0.66
    OR
    0.62
    N
    0.58
     AND
    0.52
     NOT
    0.52
     н
    0.48
     n
    0.48
     Ν
    0.47
    POSITIVE LOGITS
     жок
    0.48
    ToObject
    0.45
    blown
    0.43
    ไม่ได้
    0.42
     இல்லாமல்
    0.42
     نہیں
    0.42
     bukanlah
    0.41
     stehen
    0.40
     haja
    0.40
     plastik
    0.39
    Activations Density 0.013%

    No Known Activations