© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201127
    Prev
    Next
    INDEX
    Explanations

    time functions

    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_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
    鑫
    0.41
     rek
    0.40
     monod
    0.40
    こだわ
    0.39
     monoch
    0.38
    FBSDKLogin
    0.38
     programmatic
    0.38
     programmi
    0.38
     γά
    0.37
    🐵
    0.36
    POSITIVE LOGITS
    Dried
    0.41
    nerv
    0.37
    Vector
    0.36
     Dull
    0.36
    ઞ
    0.36
    Libs
    0.36
    vector
    0.36
    raviolet
    0.35
    ແມ
    0.35
    ifikat
    0.35
    Activations Density 0.000%

    No Known Activations