© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 117778
    Prev
    Next
    INDEX
    Explanations

    Traditional programming approaches

    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_38_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
    #!/
    0.44
    willReturn
    0.38
     lleva
    0.37
    istock
    0.37
    否
    0.37
    blick
    0.37
     mostr
    0.37
    <0xD6>
    0.36
     egyes
    0.36
     shellcheck
    0.36
    POSITIVE LOGITS
     قدیمی
    0.39
    乆
    0.39
    闵
    0.38
    خاب
    0.38
     archaic
    0.38
     partitioned
    0.37
     antiquated
    0.37
    缈
    0.37
     agricultural
    0.36
    ೋಪ
    0.35
    Activations Density 0.013%

    No Known Activations