© 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. 33345
    Prev
    Next
    INDEX
    Explanations

    foot

    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
    ólica
    0.41
     Weib
    0.37
    छि
    0.37
     BRCA
    0.36
    guez
    0.36
    quake
    0.36
    >;
    0.35
     bä
    0.35
    เบียน
    0.35
     Rally
    0.34
    POSITIVE LOGITS
     foot
    2.92
     Foot
    2.88
    Foot
    2.83
    foot
    2.69
     FOOT
    2.67
    FOOT
    2.52
    足
    2.31
     voet
    2.27
     Fuß
    2.22
     footer
    2.16
    Activations Density 0.002%

    No Known Activations