© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50666
    Prev
    Next
    INDEX
    Explanations

    Line

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     give
    0.49
     stabilize
    0.49
     activate
    0.46
     create
    0.43
    configure
    0.43
     make
    0.42
     configure
    0.41
    -',
    0.40
     settle
    0.39
     send
    0.38
    POSITIVE LOGITS
    StartState
    0.40
    RunWith
    0.38
    érée
    0.38
     happily
    0.38
     Pr
    0.38
    WillAppear
    0.37
     globals
    0.37
    苄
    0.36
     globally
    0.36
    Goto
    0.36
    Activations Density 0.003%

    No Known Activations