© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7443
    Prev
    Next
    INDEX
    Explanations

    proper nouns like names, companies, and political positions

    oai_token-act-pair · gemini-2.0-flash

    people's names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    наче
    -0.48
     massa
    -0.45
     rock
    -0.44
    argli
    -0.43
     Rukh
    -0.43
    脚注の使い方
    -0.43
     very
    -0.42
    nthetic
    -0.42
     extra
    -0.42
    WireFormatLite
    -0.42
    POSITIVE LOGITS
    Хьажоргаш
    0.67
     cervello
    0.67
     feroit
    0.66
     архивлан
    0.64
     giudi
    0.63
     auroit
    0.63
     Agamemnon
    0.63
     søndag
    0.61
     ThemeData
    0.60
     règne
    0.60
    Activations Density 1.121%

    No Known Activations