© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7213
    Prev
    Next
    INDEX
    Explanations

    various programming code delimiters

    oai_token-act-pair · gemini-2.0-flash

    words related to programming or code elements

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

    code

    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
     saites
    -0.57
     imageNamed
    -0.51
    styleType
    -0.50
    setAccessible
    -0.47
    siąż
    -0.47
     ruck
    -0.46
    IVEREF
    -0.46
    iformes
    -0.44
     poj
    -0.44
    Verdana
    -0.43
    POSITIVE LOGITS
    HtmlAttribute
    0.65
     nakalista
    0.60
     AppModule
    0.60
     Administrativna
    0.58
    präsident
    0.52
    %]
    0.51
    IsContent
    0.51
     neige
    0.51
     Wikimedijinoj
    0.51
    pertory
    0.50
    Activations Density 5.435%

    No Known Activations