© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86636
    Prev
    Next
    INDEX
    Explanations

    leading, primary, author

    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_23_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
     undo
    0.22
     pries
    0.22
    瓮
    0.21
     estimated
    0.21
     Computed
    0.21
     rank
    0.20
     th
    0.20
    <0xB6>
    0.20
     viet
    0.20
     pen
    0.20
    POSITIVE LOGITS
     claras
    0.29
    rashed
    0.25
     टकरा
    0.25
    графи
    0.24
     लिहाजा
    0.23
    ibraries
    0.22
    ginas
    0.22
    washington
    0.22
    ләр
    0.22
    desde
    0.22
    Activations Density 0.001%

    No Known Activations