© 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. 209067
    Prev
    Next
    INDEX
    Explanations

    stop bits, stop words, stop order, stop sound

    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_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
     durch
    0.28
     deteriorate
    0.28
     desolate
    0.27
     cà
    0.27
     insolvent
    0.26
     (
    0.26
     jahr
    0.26
    出
    0.25
     disassembly
    0.25
     forgo
    0.25
    POSITIVE LOGITS
    یم
    0.35
    on
    0.30
    am
    0.30
    ک
    0.28
    ্ল
    0.28
    res
    0.27
    Moscow
    0.27
    ja
    0.27
    ‌ها
    0.27
    T
    0.27
    Activations Density 0.007%

    No Known Activations