© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46410
    Prev
    Next
    INDEX
    Explanations

    system-user interaction context

    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
     arro
    0.43
     RENDITION
    0.39
    S
    0.38
    JI
    0.38
    Par
    0.37
     सफाया
    0.36
    T
    0.35
    Trait
    0.34
     cuadr
    0.33
     Lumin
    0.33
    POSITIVE LOGITS
     '
    0.42
     bạn
    0.40
    olites
    0.40
     trẻ
    0.38
     lớn
    0.38
     nước
    0.37
    prova
    0.37
    iosa
    0.37
    cienza
    0.37
    équ
    0.37
    Activations Density 0.242%

    No Known Activations