© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89291
    Prev
    Next
    INDEX
    Explanations

    time

    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_60_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
    ྣ
    0.47
     Another
    0.41
     Clicking
    0.36
     sống
    0.35
    altung
    0.34
    沏
    0.34
     Cliquez
    0.34
    등학교
    0.33
     यांना
    0.33
     यांची
    0.33
    POSITIVE LOGITS
     Early
    2.50
     Late
    2.08
    Early
    1.86
    Late
    1.67
     EARLY
    1.22
     Later
    0.88
     Near
    0.76
     早
    0.73
    早期
    0.68
     Earlier
    0.65
    Activations Density 0.221%

    No Known Activations