© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87767
    Prev
    Next
    INDEX
    Explanations

    syntactically

    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_3_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
     синте
    0.93
     합성
    0.91
    ுள்ளார்
    0.88
     synthesize
    0.85
    ટ
    0.80
     synthesized
    0.76
     Sint
    0.76
    Synthetic
    0.76
    عمل
    0.75
     ateliers
    0.75
    POSITIVE LOGITS
    os
    1.20
    もら
    1.09
    ın
    1.03
    un
    0.99
    is
    0.96
    nya
    0.94
    с
    0.94
    も
    0.92
    es
    0.89
    น
    0.87
    Activations Density 0.001%

    No Known Activations