© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    simplify/simplification

    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
    Mutation
    0.42
     Mutation
    0.41
    )});
    0.39
    ミュ
    0.38
    webElementGuid
    0.37
    mutation
    0.36
    uretic
    0.36
     mutation
    0.35
    ჲ
    0.35
    ogonad
    0.34
    POSITIVE LOGITS
     simplification
    2.75
     simpl
    2.73
     simplified
    2.70
     simplify
    2.67
     simplifying
    2.61
     simplicity
    2.55
    Simpl
    2.48
     simplifies
    2.47
     Simplify
    2.41
    Simplify
    2.41
    Activations Density 0.359%

    No Known Activations