© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50731
    Prev
    Next
    INDEX
    Explanations

    exudes qualities or feelings

    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_31_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
     ਖ
    0.39
     onlookers
    0.39
     enriched
    0.38
     แล
    0.37
    enriched
    0.37
    authorization
    0.36
    erais
    0.36
    separatedBy
    0.36
     सभी
    0.35
     me
    0.35
    POSITIVE LOGITS
     Tjiwarl
    0.48
    ρίου
    0.40
    icillium
    0.37
    汔
    0.36
    簧
    0.36
    安定
    0.36
     সাজেশন
    0.36
    ัติ
    0.35
    spring
    0.34
    сот
    0.34
    Activations Density 0.005%

    No Known Activations