© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2266
    Prev
    Next
    INDEX
    Explanations

    is followed by crucial, good, best, recommended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    maze
    0.42
     framing
    0.38
     remod
    0.38
    badge
    0.38
    闸
    0.38
    predicate
    0.38
     सुनी
    0.37
     *>
    0.36
     sheet
    0.36
    orney
    0.36
    POSITIVE LOGITS
     empfohlen
    0.43
     asynchronous
    0.42
     recommended
    0.42
     important
    0.41
    Recommended
    0.41
     Recommended
    0.39
     UserManager
    0.39
     accomplishments
    0.38
     unreliable
    0.38
    ⚪
    0.38
    Activations Density 0.174%

    No Known Activations