© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65720
    Prev
    Next
    INDEX
    Explanations

    fractions and ratios

    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_41_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
     Two
    1.22
    Two
    1.19
     two
    1.15
    two
    1.08
    ⅔
    1.07
     двух
    1.03
     दो
    0.96
     deux
    0.95
    TWO
    0.93
     två
    0.92
    POSITIVE LOGITS
     йөк
    0.40
    alogical
    0.38
     ойнойт
    0.38
     playfully
    0.37
    BackColor
    0.37
     menghilangkan
    0.36
    roar
    0.35
     ವಿಷ
    0.35
    还
    0.35
     حفاظ
    0.34
    Activations Density 0.030%

    No Known Activations