© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256771
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    comma
    1.45
     bothered
    1.41
     acquaintances
    1.39
     '='
    1.39
     perempt
    1.37
     visualise
    1.37
     workmanship
    1.35
     debounce
    1.35
     reincarn
    1.34
    ו
    1.32
    POSITIVE LOGITS
     gern
    1.08
     hoy
    1.06
    ्यू
    1.04
    शनल
    1.04
     असतो
    1.02
     ayer
    1.01
    nemen
    1.01
    цата
    1.01
     nur
    0.99
    の中で
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.