© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140368
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations

    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_46_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
     Al
    0.58
    Al
    0.58
    Lis
    0.48
    ሚ
    0.46
     Ал
    0.41
    வே
    0.40
    Ал
    0.40
     Lis
    0.39
     הה
    0.39
     mih
    0.39
    POSITIVE LOGITS
    撮
    0.37
     น
    0.36
     webbing
    0.36
     TNF
    0.36
     Vf
    0.36
     ast
    0.35
     brim
    0.35
    屋
    0.35
     크라운
    0.35
    ந
    0.35
    Activations Density 0.026%

    No Known Activations