© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49440
    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_10_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
    <unused28>
    0.59
    swire
    0.57
     guar
    0.51
    ⅙
    0.51
    ಮಂತ್ರಿ
    0.51
    不做
    0.50
     canzone
    0.50
     terzo
    0.50
    separatedBy
    0.50
     diversi
    0.50
    POSITIVE LOGITS
    Rachel
    0.55
    Points
    0.55
    Pin
    0.54
    Foi
    0.54
    Z
    0.54
    Wheat
    0.53
    Gra
    0.53
    Mar
    0.52
    Ko
    0.52
    Veg
    0.52
    Activations Density 0.000%

    No Known Activations