© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77835
    Prev
    Next
    INDEX
    Explanations

    distribute to members

    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_29_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
    >>>
    0.37
     해도
    0.36
    只能
    0.35
     കോണ്‍
    0.35
     conundrum
    0.34
     शुक्रा
    0.34
    rawdę
    0.34
    Could
    0.34
    确实
    0.34
     जनजा
    0.34
    POSITIVE LOGITS
     both
    0.42
    दोनों
    0.40
     marginalized
    0.40
    貼
    0.39
    िया
    0.39
    both
    0.38
     marrón
    0.38
    bibitem
    0.38
     বোধ
    0.38
     Nate
    0.38
    Activations Density 0.002%

    No Known Activations