© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107403
    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_2_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
     to
    1.85
     at
    1.63
     in
    1.55
    in
    1.52
    at
    1.42
     that
    1.39
    u
    1.32
    er
    1.31
    ur
    1.30
     by
    1.22
    POSITIVE LOGITS
     aplatis
    1.16
     punctato
    1.11
     divergents
    1.05
    padă
    1.02
     rupani
    1.00
     prothorace
    0.97
     munc
    0.97
     compleja
    0.97
    होत
    0.97
    GoObject
    0.96
    Activations Density 0.000%

    No Known Activations