© 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. 31931
    Prev
    Next
    INDEX
    Explanations

    technical strings

    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
    Khe
    0.39
    າງ
    0.38
    齡
    0.37
    isty
    0.37
     condensed
    0.36
     Franch
    0.36
     Jus
    0.36
     caps
    0.36
     Toledo
    0.35
     demographic
    0.35
    POSITIVE LOGITS
    ACING
    0.41
    acés
    0.39
    瑋
    0.38
    ബ്രുവരി
    0.37
    acic
    0.37
    fZ
    0.37
    ridate
    0.37
    унд
    0.36
    ᓱ
    0.36
    報告
    0.36
    Activations Density 0.000%

    No Known Activations