© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9586
    Prev
    Next
    INDEX
    Explanations

    name

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    encountered
    0.71
    •
    0.69
    andid
    0.67
    сант
    0.67
    cdot
    0.67
    Maxim
    0.66
    perfect
    0.66
     propagated
    0.65
    ●
    0.65
    【
    0.64
    POSITIVE LOGITS
     schizophrenia
    0.81
     glutamate
    0.80
     SVM
    0.77
     autism
    0.74
     மன
    0.73
     Racism
    0.72
     cities
    0.72
     sociology
    0.71
     psychiatry
    0.71
     चु
    0.71
    Activations Density 0.002%

    No Known Activations