© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90475
    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_11_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
     rask
    0.51
     den
    0.49
     n
    0.48
     out
    0.48
     Кроме
    0.47
     flavors
    0.46
     hus
    0.46
     odor
    0.46
     says
    0.45
    ör
    0.45
    POSITIVE LOGITS
    TARGETTING
    0.57
    HomeScreen
    0.54
    㩴
    0.54
    تے
    0.53
    なが
    0.53
    Gioco
    0.52
    ButtonClicked
    0.52
     چاندی
    0.51
    璋
    0.51
    कि
    0.51
    Activations Density 0.000%

    No Known Activations