© 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. 4065
    Prev
    Next
    INDEX
    Explanations

    language related to scientific research and experimental studies

    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
     تضيفلها
    -0.93
    MessageTagHelper
    -0.88
    TypedDataSet
    -0.81
    RenderAtEndOf
    -0.80
    ContentAsync
    -0.78
    numerusform
    -0.77
    évaluateur
    -0.77
    MLLoader
    -0.73
     незавершена
    -0.72
    ConstraintMaker
    -0.71
    POSITIVE LOGITS
    يديا
    0.50
     X
    0.48
     تقدم
    0.48
     ob
    0.47
     de
    0.46
     turn
    0.46
     dis
    0.45
     di
    0.45
     const
    0.45
     pay
    0.44
    Activations Density 10.208%

    No Known Activations