© 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
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228316
    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_57_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
     προσ
    0.38
     abolished
    0.37
    ூக
    0.35
    AndroidJUnit
    0.35
    phobic
    0.34
     зат
    0.34
     仕
    0.34
     опу
    0.34
     mengisi
    0.34
     menghilangkan
    0.33
    POSITIVE LOGITS
     gez
    0.40
    胆
    0.38
     heer
    0.38
     slav
    0.38
    ogo
    0.37
     кое
    0.36
    dze
    0.35
     chez
    0.35
     Dwar
    0.35
     druž
    0.34
    Activations Density 0.000%

    No Known Activations