© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77750
    Prev
    Next
    INDEX
    Explanations

    tom

    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_53_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
     Uml
    0.42
     Weyl
    0.39
     Nxe
    0.39
     Amts
    0.39
    නී
    0.39
     Gild
    0.39
    駈
    0.38
     INCRE
    0.38
     Shal
    0.38
     essendo
    0.38
    POSITIVE LOGITS
     Tom
    0.62
    Tom
    0.57
    톰
    0.52
    Tomato
    0.51
     tomato
    0.51
     TOM
    0.50
     tomo
    0.49
     tom
    0.46
    TOM
    0.46
    トマト
    0.46
    Activations Density 0.000%

    No Known Activations