© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3661
    Prev
    Next
    INDEX
    Explanations

    Teen

    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_44_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
    从事
    0.47
    *{-
    0.42
     Clark
    0.37
     Kut
    0.37
    ਉ
    0.37
     Worthington
    0.36
     अरो
    0.35
    䏼
    0.34
     Kund
    0.34
     snippetHide
    0.34
    POSITIVE LOGITS
     favours
    0.41
     allocator
    0.37
    чной
    0.36
    рованной
    0.36
     fehlen
    0.36
    izzano
    0.36
    Manager
    0.36
     favour
    0.35
     goa
    0.35
     rng
    0.35
    Activations Density 0.019%

    No Known Activations