© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173523
    Prev
    Next
    INDEX
    Explanations

    deductible, formation, bleeds, nitrate

    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
     geändert
    0.17
     adjustments
    0.16
     polynomials
    0.16
    悳
    0.16
     undes
    0.16
     segments
    0.16
    Eres
    0.16
    ographical
    0.15
    ｕ
    0.15
     shouldn
    0.15
    POSITIVE LOGITS
    入境
    0.18
    pleo
    0.18
    饮料
    0.18
     qty
    0.18
     fotografi
    0.17
     ஓய்
    0.17
    完整的
    0.17
     minuman
    0.17
    insertCell
    0.17
     informe
    0.17
    Activations Density 0.001%

    No Known Activations