© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216374
    Prev
    Next
    INDEX
    Explanations

    just

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ->$
    0.44
     কাল
    0.43
     kamp
    0.42
    qualiter
    0.40
     ዋ
    0.40
     <%
    0.39
     Kap
    0.39
    📔
    0.38
    和一个
    0.38
     voluptates
    0.38
    POSITIVE LOGITS
    ép
    0.42
    dar
    0.37
    iod
    0.35
    ourier
    0.35
    deo
    0.34
     cri
    0.34
    achan
    0.34
    Cri
    0.34
    Ep
    0.34
     கோடி
    0.33
    Activations Density 0.003%

    No Known Activations