© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201940
    Prev
    Next
    INDEX
    Explanations

    have a good day

    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_37_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
    extends
    0.43
    ่านั้น
    0.41
    ivé
    0.41
     Iv
    0.40
    राउंड
    0.39
    alaikums
    0.38
    iquement
    0.38
     "=",
    0.38
     "=
    0.38
    padStart
    0.37
    POSITIVE LOGITS
     Advert
    0.38
     fero
    0.38
    争
    0.37
     memoranda
    0.37
    اديم
    0.37
    जर
    0.36
     reven
    0.36
     JsonResult
    0.36
     pretended
    0.35
    切れ
    0.35
    Activations Density 0.001%

    No Known Activations