© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123074
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ن
    0.76
    de
    0.74
    १
    0.73
    ੇ
    0.70
    te
    0.69
    ج
    0.68
    st
    0.67
    ون
    0.67
    á
    0.67
    ни
    0.66
    POSITIVE LOGITS
    :
    0.75
     fea
    0.64
     führ
    0.63
    ורים
    0.62
    at
    0.61
     nar
    0.61
     টে
    0.59
     fez
    0.58
     Zoll
    0.58
     nie
    0.56
    Activations Density 0.000%

    No Known Activations