© 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. 131148
    Prev
    Next
    INDEX
    Explanations

    islands

    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
    Je
    0.46
    Kia
    0.44
     Jeep
    0.43
    ason
    0.41
    Egg
    0.41
     Kipp
    0.39
    John
    0.39
     K
    0.39
     الك
    0.39
    aná
    0.38
    POSITIVE LOGITS
     rom
    0.41
    ológico
    0.40
    恒
    0.39
     roma
    0.39
     Zah
    0.39
    randn
    0.38
     zah
    0.37
     decim
    0.37
     patches
    0.37
    utional
    0.37
    Activations Density 0.000%

    No Known Activations