© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8732
    Prev
    Next
    INDEX
    Explanations

    magic numbers, voltage damage, immediate failure

    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_40_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
    uidas
    0.43
    ⠀⠀⠀⠀
    0.42
     ভুট্ট
    0.41
     الجذر
    0.41
     서버
    0.39
    JTextField
    0.38
    𝑢
    0.38
     루트
    0.38
     میراتھن
    0.37
     чере
    0.36
    POSITIVE LOGITS
     smoke
    0.71
    smoke
    0.70
    煙
    0.66
     Smoke
    0.65
    Smoke
    0.61
     Smok
    0.59
    烟
    0.59
     smok
    0.58
     smoky
    0.57
     Smoking
    0.50
    Activations Density 0.065%

    No Known Activations