© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6947
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and statistical significance indicators like p-values within scientific research papers.

    oai_token-act-pair · gemini-2.0-flash

    Scientific studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Jeografia
    -1.06
    setVerticalGroup
    -0.98
    الإنجليزية
    -0.93
    LookAnd
    -0.93
    oredCriteria
    -0.92
     AssemblyProduct
    -0.85
     ویکی‌پدی
    -0.82
    PropertyChanging
    -0.82
     فريبيس
    -0.81
    principalTable
    -0.81
    POSITIVE LOGITS
    IntentFilter
    0.41
    ಂಡ
    0.33
    unesse
    0.33
    достатки
    0.32
    DEAL
    0.31
     tchèque
    0.31
    ceria
    0.30
    tures
    0.30
    #+#
    0.30
    crollView
    0.30
    Activations Density 9.910%

    No Known Activations