© 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. 52465
    Prev
    Next
    INDEX
    Explanations

    code and math

    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
     +-
    0.45
     ९
    0.44
     ७
    0.41
     ~
    0.39
     ≈
    0.38
    бата
    0.37
     ۹
    0.37
     txn
    0.36
     ±
    0.36
     ০
    0.36
    POSITIVE LOGITS
    (!
    0.41
    Tools
    0.40
    Compl
    0.40
    Cookies
    0.39
     underlines
    0.38
    Math
    0.38
    alá
    0.38
    exam
    0.38
    पूर्वक
    0.37
    Mods
    0.37
    Activations Density 0.006%

    No Known Activations