© 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. 28573
    Prev
    Next
    INDEX
    Explanations

    `: as organized`

    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
     oído
    0.38
     ワ
    0.37
     похо
    0.35
    恁
    0.35
    ervasyon
    0.34
    istič
    0.34
    
    0.34
    iet
    0.33
    阍
    0.33
    চ্ছিলেন
    0.33
    POSITIVE LOGITS
    如下
    1.13
    ดัง
    0.99
     както
    0.98
     as
    0.97
     ดัง
    0.86
     كما
    0.80
    如下图
    0.75
    如图
    0.70
     као
    0.63
     다음과
    0.57
    Activations Density 0.028%

    No Known Activations