© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226360
    Prev
    Next
    INDEX
    Explanations

    youtube.com/ links

    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_10_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
    c
    0.72
    dangerous
    0.67
     mislead
    0.64
     dangerous
    0.63
     prohibit
    0.63
     dangereux
    0.62
     antecedent
    0.62
    ?
    0.62
     страш
    0.61
    ;
    0.61
    POSITIVE LOGITS
    ai
    0.73
    á
    0.73
    ലു
    0.64
    ong
    0.62
    ﻰ
    0.62
    ONG
    0.61
    ik
    0.59
    ى
    0.59
    ie
    0.58
    س
    0.58
    Activations Density 0.005%

    No Known Activations