© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76618
    Prev
    Next
    INDEX
    Explanations

    ending turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    words
    0.34
    短
    0.33
    VQ
    0.33
    :”
    0.32
    ''_
    0.32
    简称
    0.31
    "<<
    0.31
    kubectl
    0.31
    ouv
    0.30
    _"
    0.30
    POSITIVE LOGITS
     уго
    0.38
     Triumph
    0.35
     యువ
    0.34
     Whether
    0.32
     triumph
    0.32
     informative
    0.32
     ដ
    0.32
     uniforme
    0.32
     উপসং
    0.32
     returning
    0.32
    Activations Density 0.057%

    No Known Activations