© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88806
    Prev
    Next
    INDEX
    Explanations

    universities

    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_23_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
     Cup
    0.30
     cup
    0.30
     youtube
    0.30
    辈
    0.30
     CAD
    0.29
     needs
    0.29
    youtube
    0.29
     chuyên
    0.29
     ‘
    0.29
     Cai
    0.29
    POSITIVE LOGITS
     raíz
    0.37
     raiz
    0.36
    Celula
    0.34
    ীপ
    0.34
     semisimple
    0.34
     ಸಂಸ್ಥ
    0.33
    蹌
    0.33
    numOf
    0.33
    ஸ்ரீ
    0.32
     oportunidad
    0.32
    Activations Density 0.005%

    No Known Activations