© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198868
    Prev
    Next
    INDEX
    Explanations

    durability; ward off; western

    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_15_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
     greatly
    0.54
     vastly
    0.51
    in
    0.50
     leaks
    0.48
    Με
    0.48
    Τ
    0.47
    ן
    0.47
     {
    0.47
     significantly
    0.46
    А
    0.46
    POSITIVE LOGITS
    arlan
    0.54
    嬠
    0.51
    ⚋
    0.46
    ++)//
    0.46
    rova
    0.44
    ობის
    0.44
    ऊन
    0.44
    ArchiveAction
    0.44
     também
    0.43
    enging
    0.43
    Activations Density 0.000%

    No Known Activations