© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13072
    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_40_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
    ılması
    0.42
    garakan
    0.38
    ោក
    0.37
    ଷ୍
    0.37
    iliter
    0.36
    ilis
    0.36
    orbid
    0.36
    🫦
    0.36
    زب
    0.36
     ornare
    0.35
    POSITIVE LOGITS
     intérieur
    0.49
     contour
    0.39
     qualifications
    0.38
     Interiors
    0.38
     contours
    0.38
     default
    0.38
     brou
    0.37
     Bragg
    0.37
     Bruder
    0.37
     Tilt
    0.36
    Activations Density 0.000%

    No Known Activations