© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139154
    Prev
    Next
    INDEX
    Explanations

    convinced

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    栊
    0.36
    捙
    0.33
    ৳
    0.33
    CMR
    0.33
     ല
    0.32
    你想
    0.32
     chum
    0.32
    𐰴
    0.31
    かっ
    0.31
     ভাব
    0.31
    POSITIVE LOGITS
     conviction
    2.67
     convinced
    2.52
     Conv
    2.28
     убе
    2.28
     convince
    2.23
    conv
    2.20
     convictions
    2.19
    Conv
    2.17
     convinces
    2.11
     convain
    2.06
    Activations Density 0.078%

    No Known Activations