© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38960
    Prev
    Next
    INDEX
    Explanations

    Group 1, 2, 3, ID

    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_3_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
    도
    0.62
    착
    0.58
    ш
    0.54
    ও
    0.54
    tent
    0.54
    tf
    0.53
     in
    0.52
     তুলে
    0.52
    kala
    0.52
    dw
    0.51
    POSITIVE LOGITS
    งาม
    0.56
     LSP
    0.55
    b
    0.54
     сообщи
    0.53
    isyon
    0.53
    <h4>
    0.52
     RTL
    0.52
    ंटिक
    0.52
     SBT
    0.50
     ICRC
    0.50
    Activations Density 0.022%

    No Known Activations