© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85083
    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_23_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
    蚪
    0.46
     salivary
    0.45
     blushed
    0.43
    <0x18>
    0.42
     justamente
    0.42
     feather
    0.41
    r
    0.41
     samurai
    0.41
    putable
    0.41
    ”!
    0.40
    POSITIVE LOGITS
     उमर
    0.57
     använder
    0.55
    ח
    0.54
     està
    0.50
    الي
    0.49
    餬
    0.49
    ías
    0.49
     exponer
    0.48
    ལ
    0.48
     används
    0.47
    Activations Density 0.000%

    No Known Activations