© 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. 25690
    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_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
    <unused644>
    0.63
     anderer
    0.61
     증가
    0.56
    thisTrack
    0.56
    fdPar
    0.56
     anderen
    0.54
     السيارة
    0.54
    tbLabel
    0.54
    lbrakk
    0.54
    Defocused
    0.54
    POSITIVE LOGITS
    s
    0.55
     finished
    0.50
    ↵
    0.48
     reso
    0.47
     Death
    0.46
    e
    0.44
     clock
    0.43
    o
    0.43
     trigger
    0.43
     death
    0.42
    Activations Density 0.000%

    No Known Activations