© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139109
    Prev
    Next
    INDEX
    Explanations

    *

    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_46_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
     gobl
    0.42
     daj
    0.38
    createComponent
    0.37
    ギ
    0.37
     streamer
    0.36
     tarifas
    0.36
     Present
    0.36
     gatos
    0.36
     gastron
    0.35
     restaurante
    0.35
    POSITIVE LOGITS
     XY
    0.41
    XY
    0.41
     refrained
    0.41
    zym
    0.40
     shrugged
    0.40
    ..--
    0.39
    ৃত্বে
    0.39
    */}
    0.39
     Ebert
    0.38
    Vx
    0.38
    Activations Density 0.001%

    No Known Activations