© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231303
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
     aryl
    1.09
    lja
    1.04
     ()=>
    1.03
    uje
    0.94
     inactivated
    0.94
     Pue
    0.94
     (')
    0.93
    (
    0.93
    lardan
    0.91
     epile
    0.89
    POSITIVE LOGITS
    un
    1.54
    ul
    1.44
    is
    1.26
    im
    1.23
    as
    1.22
    ur
    1.12
    기
    1.12
    ų
    1.11
    ad
    1.10
    ர்
    1.02
    Activations Density 0.000%

    No Known Activations