© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217433
    Prev
    Next
    INDEX
    Explanations

    helplines

    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_47_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
    ครื่อง
    0.38
    Benzoimidazol
    0.37
    က်
    0.37
    弥
    0.37
    ónico
    0.37
    дца
    0.37
    彌
    0.37
    roga
    0.36
    SED
    0.36
     regenerated
    0.36
    POSITIVE LOGITS
    querySelector
    0.44
    术
    0.39
    PSC
    0.39
    ска
    0.39
     PSC
    0.38
    IsNullOrEmpty
    0.38
    MoO
    0.37
     Sherwood
    0.37
    術
    0.37
     Orleans
    0.36
    Activations Density 0.000%

    No Known Activations