© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39490
    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_3_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
    Eff
    0.72
    Signal
    0.70
     in
    0.70
    7
    0.68
    Ef
    0.68
    F
    0.68
    内
    0.67
    World
    0.67
    C
    0.67
    Leg
    0.64
    POSITIVE LOGITS
    то
    0.82
    ंतर
    0.75
     venced
    0.75
    нти
    0.71
    тили
    0.71
    нта
    0.65
     vencedor
    0.64
     фонда
    0.64
    ிட்ட
    0.62
     angled
    0.62
    Activations Density 0.000%

    No Known Activations