© 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. 4066
    Prev
    Next
    INDEX
    Explanations

    URL, request, architecture, layers, function

    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
     “
    0.20
    0.17
    ,
    0.17
    “
    0.17
     performance
    0.16
    RT
    0.16
     in
    0.16
     as
    0.16
     I
    0.15
     mixed
    0.15
    POSITIVE LOGITS
    鯊
    0.19
    GALAD
    0.18
    钥
    0.18
    <unused662>
    0.18
    獗
    0.18
     ない
    0.17
     শতা
    0.17
    儉
    0.17
    癇
    0.17
     thisobject
    0.17
    Activations Density 0.094%

    No Known Activations