© 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. 32705
    Prev
    Next
    INDEX
    Explanations

    definitions and conditions

    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
     beans
    0.41
     plums
    0.40
     usia
    0.37
    狼
    0.36
     crops
    0.35
    কল
    0.35
     apricots
    0.34
     melons
    0.34
     soggetto
    0.34
     wolves
    0.34
    POSITIVE LOGITS
     Зо
    0.45
     когда
    0.43
     န
    0.41
     عندما
    0.41
     perquè
    0.40
     omdat
    0.40
     perchè
    0.39
     ፓ
    0.38
     Nosotros
    0.38
     सिलसिला
    0.38
    Activations Density 0.014%

    No Known Activations