© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246508
    Prev
    Next
    INDEX
    Explanations

    sequence homology alignment conserved

    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_40_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
     Ember
    0.45
    밴
    0.44
     ember
    0.41
     బ్రి
    0.41
     брон
    0.40
    Ast
    0.39
    Donnell
    0.39
     Xmas
    0.38
     Astro
    0.37
     toug
    0.37
    POSITIVE LOGITS
    ictionaries
    0.39
     cellulaire
    0.39
    )||
    0.38
     célula
    0.38
    Registers
    0.38
     cellular
    0.37
    annels
    0.37
    cellular
    0.37
    PPAR
    0.37
    zten
    0.36
    Activations Density 0.003%

    No Known Activations