© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105860
    Prev
    Next
    INDEX
    Explanations

    catalyze oxidative reactions

    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_1_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
    ل
    1.05
     It
    0.96
    o
    0.91
    さ
    0.88
    с
    0.88
    و
    0.87
    し
    0.85
    It
    0.84
    ↵
    0.80
     But
    0.80
    POSITIVE LOGITS
     avaient
    1.05
     auront
    0.84
    :
    0.83
     avevano
    0.81
     thiab
    0.80
     elke
    0.79
     affiliations
    0.77
     auraient
    0.77
     ajustes
    0.76
     hommage
    0.76
    Activations Density 0.002%

    No Known Activations