© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217502
    Prev
    Next
    INDEX
    Explanations

    io library

    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_31_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
     жё
    0.38
    Pax
    0.35
     ενώ
    0.35
    SPC
    0.35
    .+
    0.34
    Hist
    0.34
    电源
    0.33
    촛
    0.33
     बरबाद
    0.32
    ْد
    0.32
    POSITIVE LOGITS
     substitute
    0.37
     caption
    0.35
     সপ্তাহে
    0.35
     დღ
    0.34
     вычисли
    0.34
    passed
    0.34
     frost
    0.34
     पैर
    0.34
     costume
    0.34
     rites
    0.34
    Activations Density 0.002%

    No Known Activations