© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43170
    Prev
    Next
    INDEX
    Explanations

    code numbers 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_22_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
    ່າ
    0.45
    EnableCOMDAT
    0.42
     glam
    0.41
    拍
    0.41
    repair
    0.41
     entrepreneur
    0.40
     মুক্তিযুদ্ধের
    0.40
     répar
    0.39
    Bounce
    0.39
    歪
    0.39
    POSITIVE LOGITS
     üç
    0.44
     birinci
    0.44
    abla
    0.44
     fills
    0.43
    buton
    0.43
     PDF
    0.43
    ativen
    0.41
     디
    0.41
     테이블
    0.41
    ativa
    0.41
    Activations Density 0.000%

    No Known Activations