© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209795
    Prev
    Next
    INDEX
    Explanations

    biological filtration and anaerobic digestion

    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_20_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
    బీ
    0.36
    क्ताओं
    0.35
     ಕೊಟ್ಟ
    0.34
    كُمْ
    0.33
     социальной
    0.33
    ក្រោយ
    0.33
    ႃ
    0.33
    ۈ
    0.32
    ETHER
    0.32
     معاش
    0.32
    POSITIVE LOGITS
     speck
    0.40
     overall
    0.34
    clf
    0.34
     op
    0.31
     βαθ
    0.31
    udd
    0.30
     समग्र
    0.30
     e
    0.30
    op
    0.30
    smith
    0.30
    Activations Density 0.001%

    No Known Activations