© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131413
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
     B
    0.48
    brane
    0.43
     brane
    0.40
     br
    0.39
    br
    0.38
    BR
    0.38
     AM
    0.37
    บร
    0.36
     রহমান
    0.36
     Б
    0.35
    POSITIVE LOGITS
     산
    0.47
     Sandra
    0.46
     Sanford
    0.44
    サン
    0.43
    億
    0.41
    WQ
    0.40
    ಗ್ಗೆ
    0.39
     Santa
    0.39
     टा
    0.39
     Elf
    0.39
    Activations Density 0.000%

    No Known Activations