© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175232
    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_20_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
    usura
    0.44
    וס
    0.42
    )$,
    0.42
     Gelände
    0.42
     Laird
    0.41
     kháng
    0.41
    ✪
    0.41
    ব
    0.40
    ﺵ
    0.40
    饌
    0.39
    POSITIVE LOGITS
    iny
    0.48
    System
    0.44
     berisi
    0.44
    inoj
    0.44
     apologizing
    0.43
     sistem
    0.43
    ိတ်
    0.42
    innen
    0.42
    destroy
    0.41
    liny
    0.41
    Activations Density 0.000%

    No Known Activations