© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164467
    Prev
    Next
    INDEX
    Explanations

    oversight bodies, powers, or related actions

    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_13_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
    வச
    0.16
    purch
    0.16
    恶
    0.15
    <start_of_image>
    0.15
    those
    0.15
    বিক
    0.15
    يس
    0.15
    дек
    0.15
    тинг
    0.15
    Jessica
    0.15
    POSITIVE LOGITS
     더
    0.23
     คู่
    0.23
     맨
    0.22
     όπως
    0.22
     ให้
    0.22
     చేసే
    0.22
     하고
    0.22
     didReceive
    0.21
     curve
    0.21
     가지
    0.21
    Activations Density 0.006%

    No Known Activations