© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209552
    Prev
    Next
    INDEX
    Explanations

    mood and tone descriptors

    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_19_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
    においては
    0.30
    ഷ
    0.28
    บน
    0.25
    getProduct
    0.25
     aut
    0.24
    就好了
    0.24
     autos
    0.24
    κολ
    0.24
    孭
    0.24
    cije
    0.23
    POSITIVE LOGITS
     Offensive
    0.29
     др
    0.28
     Послед
    0.27
     इन्हीं
    0.27
     прилага
    0.26
    ума
    0.26
    ὸ
    0.26
    掩
    0.26
     playful
    0.26
     Sofa
    0.26
    Activations Density 0.027%

    No Known Activations