© 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. 23973
    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_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
     que
    0.68
    that
    0.58
     that
    0.52
    极
    0.48
     që
    0.47
     που
    0.46
     Que
    0.45
    Que
    0.45
    que
    0.44
     الذي
    0.43
    POSITIVE LOGITS
     Benedict
    0.39
    UATION
    0.38
     उग
    0.38
    われている
    0.36
     Precinct
    0.36
    蹰
    0.36
     Пре
    0.35
     Cricket
    0.35
     NRL
    0.35
     महि
    0.35
    Activations Density 0.000%

    No Known Activations