© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32863
    Prev
    Next
    INDEX
    Explanations

    bend

    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_50_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
     бен
    0.50
     bench
    0.46
    Bench
    0.45
     Bench
    0.44
    Benz
    0.43
    벤
    0.43
    ベン
    0.43
     Бен
    0.42
    Benchmark
    0.42
     benz
    0.42
    POSITIVE LOGITS
    ween
    0.38
    轪
    0.37
     нем
    0.37
    jamin
    0.37
     Add
    0.36
    reliability
    0.35
    噩
    0.35
    add
    0.34
    othy
    0.34
     εφ
    0.34
    Activations Density 0.001%

    No Known Activations