© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48577
    Prev
    Next
    INDEX
    Explanations

    *ret*, *ando*, *aprendizaje*, *muchas*

    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_10_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
     temer
    0.53
     battling
    0.52
     Hurricanes
    0.52
    atoare
    0.52
    🦯
    0.52
    ваем
    0.51
    тических
    0.50
     Pacquiao
    0.50
     Goni
    0.49
    तूल
    0.48
    POSITIVE LOGITS
    ir
    0.60
    ki
    0.60
    g
    0.55
    LOVE
    0.54
    BP
    0.53
    re
    0.53
    ANY
    0.52
    na
    0.51
    ch
    0.50
    how
    0.50
    Activations Density 0.000%

    No Known Activations