© 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. 218355
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    精灵
    0.40
    عل
    0.38
     лучше
    0.37
    滂
    0.37
    Foster
    0.37
     phenotypes
    0.37
    ంది
    0.36
    睿
    0.35
     Descriptions
    0.34
    Descriptions
    0.34
    POSITIVE LOGITS
     debtor
    0.43
     preceded
    0.41
     gira
    0.41
     hostile
    0.40
     Type
    0.39
     kitten
    0.38
     hitched
    0.38
     tipo
    0.38
    のも
    0.37
     reactionary
    0.37
    Activations Density 0.000%

    No Known Activations