© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10460
    Prev
    Next
    INDEX
    Explanations

    bits of code or mark up, chemical formulas, and maybe dates and times

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    <i>
    -1.02
    </i>
    -1.00
     
    -0.98
    <sub>
    -0.98
    <u>
    -0.94
    <code>
    -0.94
    <b>
    -0.94
    <sup>
    -0.88
    <em>
    -0.82
    </u>
    -0.81
    POSITIVE LOGITS
    RegressionTest
    0.60
     FetchType
    0.52
    posedge
    0.50
    <bos>
    0.47
    tional
    0.45
    minecraft
    0.44
    uset
    0.42
     Мекси
    0.42
    fl
    0.41
     bat
    0.41
    Activations Density 1.667%

    No Known Activations