© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201117
    Prev
    Next
    INDEX
    Explanations

    4 Ps

    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_46_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
     four
    0.66
    four
    0.59
    Four
    0.59
     Four
    0.57
     četiri
    0.55
     चार
    0.54
    四
    0.54
     четы
    0.53
     நான்கு
    0.53
     čtyř
    0.53
    POSITIVE LOGITS
     سلط
    0.43
     edged
    0.38
     gib
    0.36
     originales
    0.36
    ഏ
    0.35
     ориги
    0.34
    隻
    0.34
     lê
    0.34
    เชิง
    0.34
    ตอน
    0.34
    Activations Density 0.003%

    No Known Activations