© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16594
    Prev
    Next
    INDEX
    Explanations

    1966 and 1967

    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
    ).__
    0.30
     Cree
    0.28
     Twe
    0.27
     लूट
    0.27
    ોર્
    0.26
    twe
    0.26
     Pinto
    0.25
     ピン
    0.25
    Truman
    0.25
    俅
    0.25
    POSITIVE LOGITS
     undergoing
    0.28
     wechseln
    0.26
     blinding
    0.26
     switch
    0.26
     좋습니다
    0.26
    정보
    0.25
    istisch
    0.25
     pull
    0.25
    switch
    0.25
     processed
    0.25
    Activations Density 0.010%

    No Known Activations