© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172981
    Prev
    Next
    INDEX
    Explanations

    currently followed by an action

    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_20_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
    か
    0.45
    能
    0.42
    要
    0.39
    و
    0.39
    用于
    0.39
     guacamole
    0.38
     whatsapp
    0.38
    u
    0.38
     articoli
    0.38
     العنوان
    0.37
    POSITIVE LOGITS
     পরিবর্তনের
    0.46
     संक्रमण
    0.40
     blessed
    0.39
     Throwable
    0.38
     Coolidge
    0.38
    orphic
    0.38
     बदलने
    0.38
     শরৎ
    0.38
    ্ডার
    0.38
     Mx
    0.38
    Activations Density 0.001%

    No Known Activations