© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4582
    Prev
    Next
    INDEX
    Explanations

    code-related terms like import statements, code elements, and XML-related keywords.

    oai_token-act-pair · gemini-2.0-flash

    programming terms and XML attributes

    np_token-act-pair-logits · gpt-4o-mini

    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_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
    .
    -1.19
     the
    -0.84
     
    -0.82
    ,
    -0.79
     a
    -0.79
    -
    -0.78
     and
    -0.77
    ’
    -0.77
    '
    -0.77
    :
    -0.75
    POSITIVE LOGITS
     propOrder
    1.49
    RenderAtEndOf
    1.48
     дописавши
    1.44
     Theſe
    1.43
    ValueStyle
    1.42
    存于互联网档案馆
    1.42
    ConstraintMaker
    1.42
    Personendaten
    1.41
     ModelExpression
    1.40
     autorytatywna
    1.36
    Activations Density 1.198%

    No Known Activations