© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 122193
    Prev
    Next
    INDEX
    Explanations

    thinking followed by punctuation or common phrases

    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_38_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
     harsh
    0.43
     briefly
    0.38
    赦
    0.36
    Вт
    0.35
     Avg
    0.35
     motivations
    0.34
    localVar
    0.33
    णि
    0.33
    Brief
    0.33
     trustworthiness
    0.32
    POSITIVE LOGITS
    plicate
    0.44
     singly
    0.41
    认为是
    0.38
    noop
    0.38
     betrachtet
    0.38
     केंद
    0.37
    ieuse
    0.37
    单
    0.37
    觉得
    0.37
     मानने
    0.37
    Activations Density 0.003%

    No Known Activations