© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21399
    Prev
    Next
    INDEX
    Explanations

    Lorem Ipsum

    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_56_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
     ॥
    0.37
     Puzzle
    0.37
    🎪
    0.36
    🔦
    0.36
    itada
    0.35
     অবদান
    0.35
    🌒
    0.35
     ။
    0.34
     chutney
    0.34
    attva
    0.34
    POSITIVE LOGITS
     Lorem
    1.48
    Lorem
    1.43
     lorem
    1.26
    orem
    1.13
     ipsum
    0.94
    Etiam
    0.93
    OREM
    0.90
     Ipsum
    0.89
     Lore
    0.85
     lore
    0.82
    Activations Density 0.009%

    No Known Activations