© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    technical details and jargon relating to motorcycles, including prices

    oai_token-act-pair · gemini-2.0-flash

    programming or technical jargon

    np_token-act-pair-logits · gpt-4o-mini
    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
     للمعارف
    -0.65
     ujednoznacz
    -0.64
    localctx
    -0.62
    LookAnd
    -0.60
     beginnetje
    -0.60
     kaarangay
    -0.58
    webElementXpaths
    -0.57
    WriteLiteral
    -0.56
    SourceChecksum
    -0.56
    Ārējās
    -0.54
    POSITIVE LOGITS
     FetchType
    0.61
    rativo
    0.54
     Kag
    0.54
    ftagPool
    0.50
    AddHtmlAttribute
    0.50
    extAlignment
    0.49
    arpa
    0.49
    zadas
    0.49
    Kag
    0.47
    APL
    0.47
    Activations Density 0.515%

    No Known Activations