© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 233937
    Prev
    Next
    INDEX
    Explanations

    Heritage

    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
     Trail
    0.40
    Trails
    0.39
     Preservation
    0.37
     इंस्टीट
    0.37
    Trail
    0.36
     corporis
    0.36
    Conservation
    0.35
    慝
    0.35
     trail
    0.35
     پسند
    0.35
    POSITIVE LOGITS
    вини
    0.41
    submenu
    0.39
    darkMode
    0.37
     centerX
    0.36
     ank
    0.36
    idina
    0.36
    spanning
    0.36
    혜
    0.36
    limit
    0.35
     manoeuv
    0.35
    Activations Density 0.000%

    No Known Activations