© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2351
    Prev
    Next
    INDEX
    Explanations

    code snippets containing URLs and routes

    oai_token-act-pair · gemini-2.0-flash

    URL-related terms or parameters

    np_token-act-pair-logits · gpt-4o-mini

    url

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Efq
    -0.91
    تقاوى
    -0.91
     مشين
    -0.88
     myſelf
    -0.81
    RenderAtEndOf
    -0.80
     DBNull
    -0.76
     StatefulWidget
    -0.75
     propOrder
    -0.75
     itſelf
    -0.74
    ScopeManager
    -0.72
    POSITIVE LOGITS
     leading
    0.47
     tran
    0.46
    ري
    0.46
     frag
    0.45
     sal
    0.44
     trans
    0.43
    leading
    0.41
     transferred
    0.41
     ni
    0.40
     di
    0.40
    Activations Density 2.252%

    No Known Activations