© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42698
    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
    ي
    1.03
    י
    1.01
    ли
    0.94
    ле
    0.80
     urmă
    0.80
    ่
    0.80
    л
    0.79
    ем
    0.78
    נו
    0.77
    ι
    0.77
    POSITIVE LOGITS
    at
    1.08
    ere
    0.82
    are
    0.82
    as
    0.80
    tickers
    0.80
    av
    0.80
    BI
    0.75
    aan
    0.72
    to
    0.72
    aging
    0.71
    Activations Density 0.000%

    No Known Activations