© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136263
    Prev
    Next
    INDEX
    Explanations

    color values or names

    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_37_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
     prosedur
    0.41
     kaik
    0.39
    arsi
    0.38
    portivo
    0.38
     airliner
    0.37
     स्टोक्स
    0.37
     procedure
    0.37
    舀
    0.37
    ïdes
    0.36
    给自己
    0.36
    POSITIVE LOGITS
    chrome
    0.48
     تتع
    0.40
    Chrome
    0.39
    拵
    0.39
     chrome
    0.38
     ಕಾಣ
    0.38
    Чер
    0.38
    畱
    0.37
    كشن
    0.37
     والا
    0.36
    Activations Density 0.000%

    No Known Activations