© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76362
    Prev
    Next
    INDEX
    Explanations

    до + Russian suffix/word

    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
    قف
    0.40
    អាច
    0.40
    вые
    0.40
     jumper
    0.39
    
    0.39
    nc
    0.37
    corto
    0.37
    픕
    0.37
    名的
    0.37
    gios
    0.37
    POSITIVE LOGITS
     Boxing
    0.44
     peace
    0.42
     dignity
    0.41
    Boxing
    0.39
     boxing
    0.38
     Peace
    0.38
    Peace
    0.38
    」「
    0.37
    boxing
    0.37
    和平
    0.37
    Activations Density 0.001%

    No Known Activations