© 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. 218438
    Prev
    Next
    INDEX
    Explanations

    both followed by a comparison

    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
    劉
    0.41
     arquitectura
    0.40
    ポイント
    0.38
     toilette
    0.38
    URACY
    0.37
     AUTHORITY
    0.36
     adob
    0.36
     MAGAZINE
    0.35
    彘
    0.35
     bhij
    0.35
    POSITIVE LOGITS
    双方
    0.44
     mutual
    0.40
    gtr
    0.40
     вза
    0.39
     lifelong
    0.37
    setPosition
    0.37
    ስተ
    0.37
    हात
    0.37
     similarities
    0.36
     keduanya
    0.36
    Activations Density 0.001%

    No Known Activations