© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6956
    Prev
    Next
    INDEX
    Explanations

    time intervals

    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_39_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
     регулярно
    0.39
     없다
    0.38
     ক্যাম্পাস
    0.38
    @]
    0.38
     পূর্ণ
    0.38
    ：（
    0.38
     funcionario
    0.36
     vollständ
    0.36
    なっている
    0.36
     없
    0.35
    POSITIVE LOGITS
    getBlock
    0.37
     balanceOf
    0.35
     bonds
    0.34
     Fatt
    0.34
     Bonds
    0.33
    tracing
    0.33
     aids
    0.33
    רית
    0.33
     অব
    0.33
    xsl
    0.33
    Activations Density 0.008%

    No Known Activations