© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17383
    Prev
    Next
    INDEX
    Explanations

    open yourself/themselves/its

    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_40_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
    ង់
    0.36
    開
    0.36
     Ez
    0.34
    insights
    0.32
     ओपी
    0.31
    abez
    0.31
     ઓ
    0.30
    夫
    0.30
     открытия
    0.29
    利
    0.29
    POSITIVE LOGITS
     Restoration
    0.37
     조성
    0.34
     removal
    0.34
     Completion
    0.33
    Thrown
    0.33
     Stripe
    0.33
    ყოფ
    0.32
     Removal
    0.32
     door
    0.32
     removed
    0.32
    Activations Density 0.024%

    No Known Activations