© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216448
    Prev
    Next
    INDEX
    Explanations

    Greenwich

    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_50_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
    trashItem
    0.42
    ASI
    0.40
    가는
    0.39
     जानी
    0.39
    épendant
    0.39
    Joan
    0.38
     江
    0.38
    হার
    0.37
     Joan
    0.37
    კის
    0.37
    POSITIVE LOGITS
     Nol
    0.50
     soot
    0.44
     Soho
    0.44
    MessageHandler
    0.41
     nog
    0.41
    Sob
    0.40
    pul
    0.40
    ᚋ
    0.40
     sot
    0.40
     विलियम
    0.39
    Activations Density 0.000%

    No Known Activations