© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60909
    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
    ида
    0.88
    с
    0.87
     técnica
    0.86
     matemática
    0.84
    ó
    0.83
     când
    0.78
     característica
    0.75
     vì
    0.74
     parecen
    0.72
    ב
    0.72
    POSITIVE LOGITS
    هم
    0.85
    i
    0.85
    u
    0.85
    p
    0.79
    y
    0.79
    ru
    0.73
    iin
    0.73
    il
    0.72
    et
    0.70
    ek
    0.70
    Activations Density 0.000%

    No Known Activations