© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22816
    Prev
    Next
    INDEX
    Explanations

    eating

    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_56_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
     eat
    2.95
     eating
    2.95
    Eating
    2.73
     eats
    2.72
    吃
    2.72
     Eating
    2.69
     Eat
    2.66
    Eat
    2.66
    eating
    2.63
     ăn
    2.56
    POSITIVE LOGITS
    izio
    0.39
     Equival
    0.38
     పరి
    0.35
    gó
    0.35
     frontal
    0.35
     FU
    0.35
     coda
    0.34
     font
    0.34
     konsumen
    0.34
    |-|-
    0.34
    Activations Density 0.044%

    No Known Activations