© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45865
    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_13_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
    ни
    0.62
    谐
    0.57
    нной
    0.50
     ferrugine
    0.49
    мого
    0.49
    槑
    0.49
    ጿ
    0.48
    🈺
    0.48
    🈶
    0.46
     pelajar
    0.46
    POSITIVE LOGITS
    et
    0.55
    hou
    0.53
    ând
    0.53
    AD
    0.52
    after
    0.52
    ACH
    0.52
    »،
    0.52
    ak
    0.52
    is
    0.50
    ou
    0.50
    Activations Density 0.000%

    No Known Activations