© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13028
    Prev
    Next
    INDEX
    Explanations

    serialization and serializable data

    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
    Academy
    0.36
     hopped
    0.36
    忘れ
    0.35
    >?,
    0.35
    Corn
    0.35
    Catalog
    0.34
     hood
    0.34
    álně
    0.34
    Serie
    0.34
    ใส่
    0.34
    POSITIVE LOGITS
     ドレス
    0.36
     гара
    0.36
    等级
    0.34
     размера
    0.34
     "*****
    0.33
     analyser
    0.33
     পারা
    0.33
     Oli
    0.33
     coda
    0.33
    𝑡
    0.32
    Activations Density 0.002%

    No Known Activations