© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3949
    Prev
    Next
    INDEX
    Explanations

    a variety of special characters, possibly indicating encoding issues or code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code or foreign language

    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
     مرئيه
    -0.85
    sizeCache
    -0.84
    脚注の使い方
    -0.81
    ValueGeneration
    -0.77
     betweenstory
    -0.75
     ainfi
    -0.74
     Italijanski
    -0.74
    Espèce
    -0.72
    нгред
    -0.71
     AssemblyTitle
    -0.70
    POSITIVE LOGITS
    ↵↵
    0.43
     disambiguazione
    0.42
     m
    0.38
    <eos>
    0.37
    linalg
    0.37
     M
    0.36
     zewnętrzne
    0.35
     h
    0.35
     B
    0.34
     long
    0.34
    Activations Density 0.046%

    No Known Activations