© 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. 6401
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, with a high focus on parentheses and quotation marks used in conjunction with code blocks

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     referenties
    -0.64
    "]);
    -0.52
    NameInMap
    -0.50
     общественного
    -0.49
    makeText
    -0.47
    rcParams
    -0.47
    RTLU
    -0.47
    ={({
    -0.46
    ')}}"
    -0.46
     [],
    -0.45
    POSITIVE LOGITS
    complexType
    0.75
    +#+
    0.68
     linkovi
    0.67
    ImageContext
    0.64
    Externé
    0.64
    geot
    0.63
    LayoutStyle
    0.60
    UnusedPrivate
    0.59
    EditorBrowsable
    0.58
    Datuak
    0.56
    Activations Density 0.143%

    No Known Activations