© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12803
    Prev
    Next
    INDEX
    Explanations

    living things organs

    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_13_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
     संर
    0.46
     ссы
    0.44
    S
    0.44
     Royale
    0.44
    साईट
    0.44
     Mimi
    0.44
    🎁
    0.43
    궜
    0.43
     nai
    0.42
    ING
    0.42
    POSITIVE LOGITS
    không
    0.48
    ിയെ
    0.42
     darwin
    0.42
    if
    0.41
    ız
    0.40
    LightTheme
    0.40
    isses
    0.39
     fällt
    0.39
    ising
    0.38
    isieren
    0.38
    Activations Density 0.030%

    No Known Activations