© 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. 8048
    Prev
    Next
    INDEX
    Explanations

    code syntax, especially delimiters and keywords related to conditional logic

    oai_token-act-pair · gemini-2.0-flash

    say "end" or "fi"

    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
     end
    -1.79
     End
    -1.62
    End
    -1.44
    end
    -1.38
     END
    -1.36
    END
    -1.20
     ends
    -1.12
     Ende
    -1.07
     ended
    -1.03
     Ends
    -1.02
    POSITIVE LOGITS
     ویکی‌پدیای
    0.69
     typelib
    0.65
    ResponseWriter
    0.59
    SBATCH
    0.57
     transfieras
    0.57
    useState
    0.56
     חיצוניים
    0.55
     AssemblyProduct
    0.55
    CloseOperation
    0.54
    usercontent
    0.54
    Activations Density 1.588%

    No Known Activations