© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214798
    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_5_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
    ne
    1.40
    ى
    1.37
    ת
    1.37
    c
    1.35
    ة
    1.26
    я
    1.21
    ing
    1.20
    ла
    1.16
    k
    1.13
    ia
    1.10
    POSITIVE LOGITS
     a
    1.49
    >
    1.19
    ’
    1.10
    ;
    1.04
     choreographed
    1.00
     stitched
    0.99
     hairdryer
    0.97
    이었
    0.95
     monitors
    0.94
     solvents
    0.93
    Activations Density 0.000%

    No Known Activations