© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2596
    Prev
    Next
    INDEX
    Explanations

    formatting punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     मो
    0.41
    mo
    0.40
    诈
    0.38
     campeonato
    0.38
     החד
    0.38
     संगठ
    0.37
     بطولة
    0.37
    亻
    0.36
     सर्क
    0.36
     Departament
    0.36
    POSITIVE LOGITS
    Globalization
    0.41
    чень
    0.41
    Authorization
    0.39
     تخ
    0.38
    idation
    0.38
     Globalization
    0.37
    achite
    0.36
     মিয়া
    0.36
    以内
    0.36
    ції
    0.36
    Activations Density 0.004%

    No Known Activations