© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42320
    Prev
    Next
    INDEX
    Explanations

    drama or dramatic

    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_13_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
     Bellevue
    0.46
    an
    0.44
     トップ
    0.43
    }={\
    0.43
     تاریخ
    0.42
     Belarusian
    0.42
     REPUBLIC
    0.42
     جميع
    0.41
    u
    0.41
    दयाल
    0.41
    POSITIVE LOGITS
    Pathway
    0.54
    {
    0.54
     ಮುಂದೆ
    0.53
    Whitelist
    0.52
    Т
    0.49
    З
    0.48
     desgaste
    0.48
     inversely
    0.47
    >
    0.47
    Turns
    0.46
    Activations Density 0.002%

    No Known Activations