© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88447
    Prev
    Next
    INDEX
    Explanations

    the key is *or* the thing is

    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_18_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
    c
    0.37
     bathroom
    0.36
    ຫລ
    0.34
    ETHOD
    0.34
     fr
    0.34
     കാരണം
    0.34
    b
    0.33
     b
    0.33
    ব
    0.33
     minimal
    0.33
    POSITIVE LOGITS
     أخرى
    0.33
    㷫
    0.33
     waarmee
    0.32
     Valverde
    0.31
    May
    0.31
     समझने
    0.31
    ಜೆ
    0.31
    нің
    0.31
    Loved
    0.31
    埶
    0.30
    Activations Density 0.005%

    No Known Activations