© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42361
    Prev
    Next
    INDEX
    Explanations

    like "X"

    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
    ﺮ
    0.24
     т
    0.24
     $
    0.22
     Subsection
    0.22
     conclusion
    0.22
     Mega
    0.22
     Micro
    0.22
     multib
    0.22
     Ма
    0.21
     L
    0.21
    POSITIVE LOGITS
    肱
    0.25
    رمپ
    0.23
    陥
    0.22
    निश्ड
    0.22
    Vorlage
    0.22
     drawRight
    0.21
    が存在
    0.21
    Zr
    0.21
    툴
    0.21
    omac
    0.21
    Activations Density 0.058%

    No Known Activations