© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14345
    Prev
    Next
    INDEX
    Explanations

    mathematical language, especially terms related to analysis, functions, and boundaries.

    oai_token-act-pair · gemini-2.0-flash

    boundary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     precisione
    -0.57
     profundos
    -0.48
    await
    -0.48
     profondità
    -0.46
     esclu
    -0.45
     meeste
    -0.44
     frequenza
    -0.44
     publicação
    -0.44
    y
    -0.44
     distribuzione
    -0.43
    POSITIVE LOGITS
    脚注の使い方
    0.91
    */].
    0.84
    '));
    0.82
    '},
    0.81
    WebElementEntity
    0.81
    ----</
    0.81
     AssemblyCulture
    0.80
    +#+#
    0.80
    انيف
    0.79
     PLWABN
    0.79
    Activations Density 4.257%

    No Known Activations