© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21261
    Prev
    Next
    INDEX
    Explanations

    es

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     diseñado
    0.49
     designed
    0.45
     Designed
    0.44
     diseñada
    0.44
    Designed
    0.39
    designed
    0.38
    履
    0.37
     meant
    0.37
    結合
    0.36
     configured
    0.34
    POSITIVE LOGITS
     decir
    0.93
     dizer
    0.56
     zeggen
    0.51
    说
    0.47
     say
    0.46
     sei
    0.46
    case
    0.45
    說
    0.44
     säga
    0.44
    قول
    0.43
    Activations Density 0.006%

    No Known Activations