© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170635
    Prev
    Next
    INDEX
    Explanations

    `sizeof` or `declaration`, `variable`

    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_20_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
     Spelling
    0.21
     Added
    0.21
     Link
    0.20
    או
    0.19
     précisément
    0.19
     ଭ
    0.19
    ameron
    0.18
     according
    0.18
    s
    0.18
     Puj
    0.18
    POSITIVE LOGITS
    북도
    0.21
    нная
    0.20
    
    0.20
    ounid
    0.20
    ный
    0.20
     पॉलिटिकल
    0.20
    𓂃
    0.20
     них
    0.20
    圴
    0.20
    bathing
    0.19
    Activations Density 0.001%

    No Known Activations