© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23716
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     RS
    0.38
     Oncol
    0.38
    嬉
    0.36
     Structure
    0.36
     civic
    0.36
     பாஜக
    0.36
    ᐱ
    0.35
    ဏ
    0.35
     trọng
    0.35
     Watershed
    0.35
    POSITIVE LOGITS
    ৯০
    0.39
    KEA
    0.38
    gas
    0.36
    搬型
    0.36
     народа
    0.35
    стная
    0.35
     عمر
    0.35
     пуль
    0.34
    ̴
    0.34
    Battery
    0.34
    Activations Density 0.003%

    No Known Activations