© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61666
    Prev
    Next
    INDEX
    Explanations

    hijos de

    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_11_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
    тни
    0.47
     Тру
    0.42
    લ્લા
    0.41
    ದಗ
    0.38
    骈
    0.38
    ாஹ
    0.38
    四年
    0.38
    怅
    0.38
    讓他
    0.38
    쯜
    0.37
    POSITIVE LOGITS
    iasis
    0.42
    Y
    0.40
     लक्ष्मीबाई
    0.39
    ส่วน
    0.39
    ي
    0.38
    ระ
    0.38
     de
    0.37
     TODO
    0.37
    &#
    0.37
    กร
    0.36
    Activations Density 0.006%

    No Known Activations