© 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. 205153
    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
     périph
    0.38
    黃
    0.38
     पड़
    0.37
    䢀
    0.37
    내는
    0.37
    Ви
    0.36
    Ка
    0.36
    АР
    0.35
     只
    0.35
     propiet
    0.35
    POSITIVE LOGITS
    authority
    0.54
     authority
    0.52
     Authority
    0.42
     AUTHORITY
    0.40
    phi
    0.39
    autorité
    0.38
    Authority
    0.38
    ingo
    0.36
     रक्षा
    0.36
     autoridad
    0.35
    Activations Density 0.000%

    No Known Activations