© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29285
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    者が
    0.46
     زیرا
    0.44
     menstrual
    0.43
    Наша
    0.43
    時間が
    0.42
     こと
    0.41
    することで
    0.41
     れ
    0.41
     hydration
    0.41
     จำนวน
    0.41
    POSITIVE LOGITS
    cek
    0.53
    ch
    0.52
    rach
    0.52
    p
    0.52
    bach
    0.52
    elan
    0.52
    glow
    0.51
    sh
    0.50
    skill
    0.50
    peed
    0.48
    Activations Density 0.000%

    No Known Activations