© 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. 194404
    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
    it
    0.59
    ar
    0.53
    {
    0.51
    o
    0.51
     personen
    0.49
     Erfolg
    0.49
    chmal
    0.49
     Begegn
    0.48
    ¸
    0.48
     Grenzen
    0.48
    POSITIVE LOGITS
    쭉
    0.47
    သွယ်
    0.47
     agreg
    0.43
    angling
    0.42
     Yank
    0.42
    ियन
    0.42
    ivers
    0.41
    conex
    0.41
    ালিয়া
    0.41
    гия
    0.40
    Activations Density 0.000%

    No Known Activations