© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45484
    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_3_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
    a
    0.86
    ه
    0.85
    r
    0.82
    ر
    0.79
    Halloween
    0.70
    ACH
    0.69
    AO
    0.69
     Bedürfnisse
    0.68
    SQLite
    0.68
    が行
    0.67
    POSITIVE LOGITS
    ला
    0.87
    azione
    0.72
     있는
    0.71
     있다
    0.71
    نی
    0.70
     ہونا
    0.70
    ی
    0.70
    한
    0.69
    تی
    0.69
     voltages
    0.69
    Activations Density 0.000%

    No Known Activations