© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 168041
    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
     (…)
    0.37
     here
    0.36
     "");
    0.36
    sty
    0.36
    只见
    0.36
     页
    0.35
    ');
    0.34
    increasing
    0.33
     fique
    0.32
    increases
    0.32
    POSITIVE LOGITS
    অন
    0.38
     Schwe
    0.36
    GED
    0.35
    ülés
    0.35
     genealogy
    0.35
     Sulf
    0.34
    [{}\
    0.33
     Licht
    0.33
    úl
    0.33
    Flam
    0.33
    Activations Density 0.000%

    No Known Activations