© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80172
    Prev
    Next
    INDEX
    Explanations

    AI and online interaction

    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_53_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
     sub
    0.41
     subst
    0.39
     ony
    0.38
     montrer
    0.36
    갬
    0.34
     prover
    0.34
    的小
    0.34
     mily
    0.34
    вот
    0.34
    的大
    0.33
    POSITIVE LOGITS
     Peng
    0.38
    тат
    0.38
    璐
    0.35
    dat
    0.35
     रहीम
    0.34
    бат
    0.34
    ats
    0.33
     गणेश
    0.33
    컬
    0.33
    дати
    0.33
    Activations Density 0.015%

    No Known Activations