© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15267
    Prev
    Next
    INDEX
    Explanations

    break down complex topics

    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_40_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
     Rely
    0.37
     veze
    0.36
     Rabbit
    0.35
     Specific
    0.34
    ][$
    0.34
     मंडळा
    0.34
    ാഗ
    0.33
     खार
    0.33
     Connection
    0.32
     nao
    0.32
    POSITIVE LOGITS
    Analysis
    0.51
    梳
    0.47
     분석
    0.46
     compiled
    0.44
     анализа
    0.43
     summarised
    0.42
     identified
    0.41
    分析
    0.40
    summar
    0.40
     Analysis
    0.40
    Activations Density 0.045%

    No Known Activations