© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207729
    Prev
    Next
    INDEX
    Explanations

    bzip2 compression commands

    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_25_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
    問題
    0.41
    ה
    0.38
    Sam
    0.38
    UN
    0.37
     проблемы
    0.37
    cv
    0.36
    Pr
    0.36
    Be
    0.36
    Ell
    0.35
    Fried
    0.35
    POSITIVE LOGITS
    estation
    0.37
    والفقار
    0.36
     yg
    0.35
     decoupled
    0.34
    룔
    0.34
     desempeño
    0.33
     TimeSpan
    0.32
     tầm
    0.32
    ಾರೆ
    0.31
    を務
    0.31
    Activations Density 0.001%

    No Known Activations