© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200843
    Prev
    Next
    INDEX
    Explanations

    modeling and modelling

    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_37_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
     model
    0.46
    厲
    0.38
    Le
    0.36
    Model
    0.36
     defendant
    0.35
    oga
    0.35
    OGA
    0.35
     modals
    0.35
     Model
    0.35
    agati
    0.35
    POSITIVE LOGITS
    слу
    0.39
    耠
    0.38
    心思
    0.35
     mengembangkan
    0.35
     immediatamente
    0.35
    jl
    0.35
    骓
    0.34
    Steps
    0.34
    क्सर
    0.34
    ങ്ങളും
    0.34
    Activations Density 0.003%

    No Known Activations