© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125038
    Prev
    Next
    INDEX
    Explanations

    Worcester, Wuhan, Worcestershire Sauce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     Comfortable
    0.42
     أقل
    0.41
    חר
    0.39
     cómodo
    0.39
    மும்
    0.39
    扪
    0.38
     Water
    0.37
    కుండా
    0.37
    ريقه
    0.37
    glTex
    0.37
    POSITIVE LOGITS
    чек
    0.36
     checkpoints
    0.34
    明治
    0.34
    ("\(
    0.34
    aux
    0.34
     signaling
    0.34
     consistency
    0.33
    륜
    0.33
     jeux
    0.32
    авто
    0.32
    Activations Density 0.000%

    No Known Activations