© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1247
    Prev
    Next
    INDEX
    Explanations

    will not, refused to

    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_40_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
    {}".
    0.38
     dépour
    0.38
     {},
    0.37
     underdeveloped
    0.35
    {})
    0.35
     {});
    0.35
     educa
    0.35
    нему
    0.35
     uncoated
    0.35
    &$
    0.34
    POSITIVE LOGITS
     refuses
    1.26
     refuse
    1.21
     refused
    1.17
     wont
    1.15
     won
    1.12
     refusing
    1.12
     wouldn
    1.11
    不会
    1.10
    Won
    1.04
    won
    1.01
    Activations Density 0.124%

    No Known Activations