© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144285
    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_0_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
    ла
    1.92
    י
    1.73
    ي
    1.66
     извест
    1.62
    ים
    1.59
    יות
    1.58
    ות
    1.52
    д
    1.49
    ться
    1.43
    esque
    1.42
    POSITIVE LOGITS
    il
    1.85
     I
    1.73
    it
    1.48
    ut
    1.48
    ON
    1.36
    AN
    1.34
    AL
    1.27
     a
    1.27
    IT
    1.27
    ER
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.