© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11723
    Prev
    Next
    INDEX
    Explanations

    superscripted exponents

    oai_token-act-pair · gemini-2.0-flash

    Math/stats notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.88
    WriteBarrier
    -0.79
    AccessorTable
    -0.79
     cherchés
    -0.78
     CreateTagHelper
    -0.76
     Loh
    -0.75
     وتسجيلات
    -0.73
    verifyException
    -0.72
    //</
    -0.72
    /******/
    -0.72
    POSITIVE LOGITS
    Див
    0.35
     olvides
    0.35
    T
    0.34
     bahç
    0.33
    Kaynakça
    0.32
     مشين
    0.32
    AttributeSet
    0.32
    tığı
    0.32
     فريبيس
    0.31
    高质量
    0.31
    Activations Density 1.694%

    No Known Activations