© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols.

    oai_token-act-pair · gemini-2.0-flash

    programming and mathematical terms

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

    mathematical/code notations

    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
    XmlAccessType
    -0.57
     فريبيس
    -0.57
    "}")
    -0.56
    phosa
    -0.56
    --)
    -0.56
    kuuta
    -0.55
    }>;
    -0.55
     onOptions
    -0.51
     Metcalf
    -0.50
    omas
    -0.50
    POSITIVE LOGITS
    abestanden
    0.64
     numberOfRows
    0.62
    ContentAlignment
    0.60
    ///</
    0.52
    DockStyle
    0.51
    CppCodeGen
    0.50
     one
    0.50
    AutoScale
    0.49
    IndentedString
    0.48
    soever
    0.47
    Activations Density 9.058%

    No Known Activations