© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108996
    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_2_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
     to
    1.06
    um
    1.03
    1.03
    are
    1.02
    can
    0.99
    ype
    0.98
    k
    0.98
    creation
    0.96
    p
    0.95
    ps
    0.95
    POSITIVE LOGITS
    ר
    1.45
    কে
    1.20
    श
    1.20
    트
    1.14
    ல்
    1.13
     conceivably
    1.09
    تي
    1.09
    К
    1.05
    ா
    1.05
    ஜ
    1.02
    Activations Density 0.000%

    No Known Activations