© 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. 2148
    Prev
    Next
    INDEX
    Explanations

    snippets of code including equal signs, brackets, and other symbols commonly used in programming languages

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

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

    brackets and parenthesis

    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
    ttemberg
    -0.72
    ativeness
    -0.70
     faſt
    -0.68
    sonian
    -0.63
    addPreferredGap
    -0.63
    Hentet
    -0.61
     ExecuteAsync
    -0.60
    abetes
    -0.60
    InSection
    -0.59
     $=\
    -0.59
    POSITIVE LOGITS
     (
    0.70
     [
    0.61
     $(
    0.54
    rån
    0.53
    $(
    0.52
    (
    0.51
     map
    0.45
     （
    0.43
    （
    0.43
    ArgumentParser
    0.42
    Activations Density 3.118%

    No Known Activations