© 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. 110500
    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
    of
    1.73
    ام
    1.27
    ات
    1.24
     to
    1.22
    를
    1.18
    ，
    1.06
    いる
    1.05
    他的
    1.02
    মেন্ট
    1.02
    ę
    1.01
    POSITIVE LOGITS
     can
    1.42
     have
    1.33
     eléct
    1.23
     has
    1.09
     случаи
    1.05
     déta
    1.05
    б
    1.02
     aborted
    1.02
    in
    1.01
    ar
    1.01
    Activations Density 0.000%

    No Known Activations