© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30013
    Prev
    Next
    INDEX
    Explanations

    configuration or initialization

    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_10_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
    in
    0.70
    7
    0.66
    ın
    0.65
    att
    0.62
    <0xB3>
    0.60
     séptimo
    0.58
    의
    0.58
    inins
    0.56
    ან
    0.56
    as
    0.55
    POSITIVE LOGITS
     to
    0.78
     a
    0.68
     or
    0.57
     x
    0.55
     is
    0.53
     sandstone
    0.53
     an
    0.53
     ampere
    0.52
     et
    0.52
    <0x80>
    0.50
    Activations Density 0.020%

    No Known Activations