© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16092
    Prev
    Next
    INDEX
    Explanations

    Supreme Court cases

    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_40_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
    肖
    0.40
    CurrentImage
    0.40
     feito
    0.37
     cristiana
    0.37
     cosmos
    0.37
    ਸੀ
    0.37
     photosphere
    0.36
    顐
    0.36
    mnop
    0.36
     voter
    0.36
    POSITIVE LOGITS
    appeal
    0.46
     appeal
    0.45
    Kol
    0.44
     appealed
    0.40
     Kol
    0.40
    Appeal
    0.39
     kol
    0.39
     appeals
    0.39
     bedste
    0.38
     Appeal
    0.38
    Activations Density 0.002%

    No Known Activations