© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33956
    Prev
    Next
    INDEX
    Explanations

    sorrow, fire, deed, striving, bias

    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
    嶉
    0.34
     ത
    0.33
    觕
    0.33
     creer
    0.31
    ಿಸುವ
    0.30
     dedica
    0.30
    鐗
    0.30
    徎
    0.30
    䛶
    0.30
     sets
    0.29
    POSITIVE LOGITS
     yukarı
    0.32
    careous
    0.31
    broken
    0.30
     فوق
    0.30
     Yukarı
    0.30
    ennials
    0.29
     '=
    0.29
    acios
    0.29
    ையான
    0.29
    scoped
    0.29
    Activations Density 0.025%

    No Known Activations