© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36642
    Prev
    Next
    INDEX
    Explanations

    ein Turing

    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_11_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
    \
    0.54
    μένα
    0.49
    s
    0.47
    astien
    0.44
    ↵
    0.44
    configured
    0.43
    euler
    0.42
    kast
    0.42
    effect
    0.42
    automated
    0.42
    POSITIVE LOGITS
     Пре
    0.50
    ’!
    0.50
    晔
    0.49
     verzi
    0.49
     problemi
    0.48
     lizenz
    0.48
     cộng
    0.47
    难度
    0.47
     courthouse
    0.47
     despre
    0.47
    Activations Density 0.010%

    No Known Activations