© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200359
    Prev
    Next
    INDEX
    Explanations

    water bears

    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_12_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
    ">=
    0.62
     Colorful
    0.54
    signUp
    0.53
    پرس
    0.53
    اعر
    0.53
    cipher
    0.53
    inputId
    0.52
     স্পষ্টভাবে
    0.52
     अपडेट
    0.50
    interpr
    0.50
    POSITIVE LOGITS
     hogs
    0.61
     flows
    0.56
     &
    0.55
     fractions
    0.54
     offices
    0.52
     sinks
    0.52
     soaps
    0.52
     brews
    0.52
     kumar
    0.52
     organs
    0.51
    Activations Density 0.002%

    No Known Activations