© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210926
    Prev
    Next
    INDEX
    Explanations

    code functions and modules

    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_20_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
     ولكن
    0.26
    BUT
    0.26
     Goode
    0.25
    ج
    0.24
    HIG
    0.24
    However
    0.23
    Initial
    0.23
    篪
    0.23
     BUT
    0.23
     عليهم
    0.23
    POSITIVE LOGITS
     Conference
    0.28
     drink
    0.28
     trademark
    0.26
    ではなく
    0.26
     presentation
    0.26
     gift
    0.25
     банков
    0.25
     fanatic
    0.25
     perdió
    0.25
     punt
    0.24
    Activations Density 0.001%

    No Known Activations