© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81074
    Prev
    Next
    INDEX
    Explanations

    coiling

    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_0_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
     (
    2.31
    ing
    1.77
    AL
    1.71
    AT
    1.58
    K
    1.58
    at
    1.52
    u
    1.52
    s
    1.50
    ik
    1.49
    一
    1.48
    POSITIVE LOGITS
     કરી
    1.54
     ﺍ
    1.48
     Фло
    1.40
    ᱝ
    1.40
     Олег
    1.39
    ری
    1.38
    いた
    1.38
     ﺍﻟ
    1.34
    ле
    1.33
     ኦ
    1.32
    Activations Density 0.001%

    No Known Activations