© 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. 32259
    Prev
    Next
    INDEX
    Explanations

    ud

    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
    ミネ
    0.40
    комп
    0.39
    படி
    0.37
     kel
    0.37
    ក
    0.35
     KNeighbors
    0.35
     ಡಿ
    0.35
    Ｑ
    0.35
     knot
    0.34
     ಕೊಡ
    0.34
    POSITIVE LOGITS
    ami
    0.43
    ano
    0.43
     ami
    0.40
    gir
    0.39
    atani
    0.39
     tuff
    0.39
    туа
    0.39
    typescript
    0.39
    gono
    0.39
    tz
    0.38
    Activations Density 0.000%

    No Known Activations