© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232524
    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_6_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
    '
    1.38
     to
    1.21
    ד
    1.05
     (
    1.04
     world
    1.00
    ST
    0.96
     you
    0.93
     with
    0.91
     that
    0.90
     wood
    0.88
    POSITIVE LOGITS
    n
    1.02
    nThe
    1.00
    t
    1.00
    ።
    0.95
    kang
    0.95
    ll
    0.91
    рифмети
    0.91
     டிகிரி
    0.90
    overline
    0.88
     exercícios
    0.88
    Activations Density 0.000%

    No Known Activations