© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35974
    Prev
    Next
    INDEX
    Explanations

    sphenoid bone, grain, spacelift

    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_3_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
    י
    0.80
    та
    0.74
    ъ
    0.70
    נ
    0.68
     empezar
    0.67
    ى
    0.67
    ة
    0.65
     préférable
    0.65
    nimmt
    0.64
    ט
    0.64
    POSITIVE LOGITS
    "
    0.74
    are
    0.73
    on
    0.65
     Expenditures
    0.64
    رج
    0.61
    foils
    0.59
    ai
    0.59
    رین
    0.58
    告示
    0.58
     Conver
    0.56
    Activations Density 0.001%

    No Known Activations