© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198329
    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_9_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
    ()\
    0.56
    Че
    0.50
    টির
    0.49
    ()
    0.48
    냈
    0.48
     Renato
    0.48
     magní
    0.48
     ArrayRef
    0.48
    Эти
    0.48
    novu
    0.48
    POSITIVE LOGITS
    ա
    0.50
     counselor
    0.49
     time
    0.47
     week
    0.46
     teaches
    0.46
     phases
    0.45
     spells
    0.45
     teach
    0.45
     አይ
    0.45
     exposed
    0.45
    Activations Density 0.000%

    No Known Activations