© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49789
    Prev
    Next
    INDEX
    Explanations

    heart shape equations

    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
     軽量
    0.39
    الج
    0.37
     परिस
    0.36
    <bbox>
    0.36
    emie
    0.35
    痺
    0.35
    姿勢
    0.35
     πάν
    0.35
     getHeight
    0.35
    鈣
    0.35
    POSITIVE LOGITS
     Anglican
    0.38
     scented
    0.38
     Brittany
    0.37
     स्वत
    0.36
     taken
    0.35
     privado
    0.35
     kinder
    0.35
     rolled
    0.35
     Euchar
    0.35
    滚
    0.34
    Activations Density 0.022%

    No Known Activations