© 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. 7039
    Prev
    Next
    INDEX
    Explanations

    code loops using incrementing or decrementing for loops in C or C++

    oai_token-act-pair · gemini-2.0-flash

    programming syntax

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

    code punctuation

    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
    x
    -0.62
    j
    -0.52
    R
    -0.52
    ende
    -0.50
    M
    -0.49
    X
    -0.48
    J
    -0.48
    EndInit
    -0.48
    --
    -0.46
    mi
    -0.46
    POSITIVE LOGITS
    NUMX
    0.92
    OOTDTY
    0.88
    CodedInputStream
    0.76
    findpost
    0.74
    esterday
    0.73
    BibitemShut
    0.72
    sữa
    0.72
    istoitu
    0.72
    tront
    0.71
    észetes
    0.71
    Activations Density 1.412%

    No Known Activations