© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112504
    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_2_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
    م
    1.30
    al
    1.13
    ن
    1.07
    র
    1.00
    ب
    0.98
    b
    0.97
     rápido
    0.93
    is
    0.92
    v
    0.92
    ח
    0.92
    POSITIVE LOGITS
    도
    0.98
    که
    0.96
    گ
    0.91
    들이
    0.89
    /
    0.88
    >
    0.88
    ’-
    0.86
    +
    0.86
                
    0.86
     eater
    0.85
    Activations Density 0.000%

    No Known Activations