© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221056
    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_31_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
    GLOBALS
    0.37
    ڑھ
    0.31
     enk
    0.29
    jahteraan
    0.29
    枋
    0.29
    ):\
    0.29
    ὰ
    0.29
    Concerning
    0.28
     capacitación
    0.28
    Floor
    0.27
    POSITIVE LOGITS
     registry
    0.35
     entourage
    0.33
     basketball
    0.32
     registries
    0.32
     knitting
    0.31
     shedding
    0.31
     drastic
    0.30
     housekeeping
    0.30
     erections
    0.30
    盻
    0.30
    Activations Density 0.000%

    No Known Activations