© 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. 199078
    Prev
    Next
    INDEX
    Explanations

    reflexes

    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
     Da
    0.66
     Dae
    0.61
    Da
    0.58
     da
    0.50
     대
    0.50
     да
    0.48
     synt
    0.46
     Đồng
    0.44
     syntactic
    0.44
     đại
    0.43
    POSITIVE LOGITS
     Reflex
    0.42
    五
    0.41
    obox
    0.40
    reflex
    0.39
     Cuff
    0.39
     Five
    0.38
    (":
    0.38
    untlet
    0.38
     )}
    0.38
     kes
    0.36
    Activations Density 0.002%

    No Known Activations