© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196427
    Prev
    Next
    INDEX
    Explanations

    bot commands

    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_27_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
     innings
    0.42
     મો
    0.41
     handkerchief
    0.41
    ᱘
    0.41
     tenor
    0.40
     preliminary
    0.40
     whey
    0.40
     lasso
    0.39
    rdquo
    0.39
     premature
    0.38
    POSITIVE LOGITS
    Provider
    0.42
     ডিজ
    0.42
    ientôt
    0.41
     Roblox
    0.41
     utrzym
    0.40
    谪
    0.40
    柠
    0.39
    État
    0.39
    등급
    0.38
     관련된
    0.37
    Activations Density 0.000%

    No Known Activations