© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52392
    Prev
    Next
    INDEX
    Explanations

    settings, options, parameters

    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_30_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
     жү
    0.29
     Gallows
    0.29
     hätte
    0.29
     Reason
    0.29
     কারও
    0.28
    귤
    0.28
    ﮏ
    0.28
     stry
    0.27
    သား
    0.27
     shuttle
    0.27
    POSITIVE LOGITS
     θε
    0.32
    Disclaimer
    0.30
    igna
    0.30
    ()">
    0.30
    lige
    0.29
    Father
    0.29
    सेट
    0.29
    Anche
    0.29
    Robert
    0.29
    sem
    0.28
    Activations Density 0.003%

    No Known Activations