© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    do / làm

    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
     Action
    0.43
     핸
    0.41
     एक्शन
    0.41
    Action
    0.40
     ACTION
    0.39
    핸
    0.38
     χει
    0.35
     acción
    0.35
     Nath
    0.35
    手
    0.35
    POSITIVE LOGITS
    Do
    0.50
    do
    0.47
     Do
    0.47
    Doing
    0.47
     do
    0.43
     करण्यास
    0.42
     doen
    0.41
    doing
    0.41
    Sigma
    0.40
    ทำ
    0.40
    Activations Density 0.013%

    No Known Activations