© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207675
    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_25_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
    Þ
    0.39
     Opp
    0.39
     Deal
    0.38
    owska
    0.38
    se
    0.38
     S
    0.37
    avan
    0.37
     Row
    0.37
    Ε
    0.37
    they
    0.37
    POSITIVE LOGITS
     personal
    0.42
     listener
    0.40
     mécanismes
    0.40
     للت
    0.39
     disk
    0.38
    ({});
    0.38
     తమిళ
    0.38
     bekerja
    0.38
     tùy
    0.38
     kiş
    0.37
    Activations Density 0.000%

    No Known Activations