© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 29973
    Prev
    Next
    INDEX
    Explanations

    additive or multiplicative

    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_40_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
     倍
    0.40
     कराया
    0.39
    嫨
    0.38
     奥
    0.38
     lom
    0.38
    മാണ്
    0.36
     Одна
    0.36
    の上
    0.36
    рін
    0.35
    朲
    0.35
    POSITIVE LOGITS
    breadcrumbs
    0.46
    container
    0.42
    жив
    0.41
     liberalism
    0.37
     academ
    0.37
    codingPath
    0.36
    oler
    0.35
     Combined
    0.35
    BTN
    0.35
    disamb
    0.35
    Activations Density 0.027%

    No Known Activations