© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52001
    Prev
    Next
    INDEX
    Explanations

    array iteration

    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_30_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
     BETWEEN
    0.38
    ElementChild
    0.35
     reloading
    0.35
     between
    0.34
     betrayal
    0.33
    🐵
    0.33
     半袖
    0.32
    estruct
    0.32
     believer
    0.32
     유
    0.32
    POSITIVE LOGITS
     متنوع
    0.33
    BDA
    0.31
    adoras
    0.30
    dera
    0.30
     DVDs
    0.30
    мет
    0.30
     டிவி
    0.30
     kita
    0.29
    हेर
    0.29
    VPS
    0.29
    Activations Density 0.003%

    No Known Activations