© 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. 59155
    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
    1.41
    ند
    1.28
    м
    1.28
    ری
    1.24
    з
    1.18
    ности
    1.16
    ्या
    1.12
    ем
    1.08
    ő
    1.08
    ン
    1.04
    POSITIVE LOGITS
     be
    1.46
    (
    1.11
    দের
    1.09
    ↵
    1.02
     have
    0.98
     haben
    0.95
    }
    0.93
    s
    0.88
     kwam
    0.86
     to
    0.85
    Activations Density 0.000%

    No Known Activations