© 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. 207310
    Prev
    Next
    INDEX
    Explanations

    places and people

    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
     trazer
    0.26
     vznik
    0.24
    带来
    0.24
     tipe
    0.24
     coordenada
    0.24
    𝓾
    0.24
     lij
    0.24
     trasera
    0.24
    дви
    0.23
    AMPLE
    0.23
    POSITIVE LOGITS
    üks
    0.25
     mixte
    0.25
     சேர்ந்து
    0.24
    誰
    0.24
     группу
    0.24
    alam
    0.24
     erneut
    0.24
     Саша
    0.23
     다시
    0.23
     Mixed
    0.23
    Activations Density 0.001%

    No Known Activations