© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137359
    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_37_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
     teclado
    0.39
    ូន
    0.38
     Heading
    0.37
     captioned
    0.37
    getBounding
    0.36
     getData
    0.36
    吺
    0.36
    Heading
    0.36
     setError
    0.36
     Caught
    0.36
    POSITIVE LOGITS
    wohl
    0.44
    payer
    0.42
    ('/').
    0.41
    adhy
    0.40
    any
    0.38
    cred
    0.38
    authState
    0.38
     भग
    0.38
    ible
    0.37
    edly
    0.37
    Activations Density 0.000%

    No Known Activations