© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234722
    Prev
    Next
    INDEX
    Explanations

    [::-1] for reversing

    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_32_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
     Metabolism
    0.39
    tiers
    0.38
    جن
    0.37
     Convolution
    0.37
    rains
    0.37
     allowances
    0.37
    罅
    0.37
     Reaction
    0.37
    Reaction
    0.36
     Acta
    0.36
    POSITIVE LOGITS
     orientação
    0.41
     orientación
    0.39
     orientation
    0.39
    ᒧ
    0.38
     reversed
    0.37
     sentido
    0.37
     negativo
    0.36
    nPortIndex
    0.36
     gär
    0.36
     recommending
    0.36
    Activations Density 0.003%

    No Known Activations