© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67475
    Prev
    Next
    INDEX
    Explanations

    dialogue end

    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_51_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
    ابل
    0.40
    phantom
    0.39
    الت
    0.38
    alon
    0.38
     bladder
    0.37
     春
    0.37
     শীতল
    0.37
    វ
    0.37
    pref
    0.36
    Cass
    0.36
    POSITIVE LOGITS
    emie
    0.40
     ತಾ
    0.40
     deserialize
    0.39
     DMS
    0.39
     모양
    0.38
     attributes
    0.37
     pygame
    0.37
     nonnegative
    0.37
     wilderness
    0.37
    athor
    0.37
    Activations Density 0.004%

    No Known Activations