© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12630
    Prev
    Next
    INDEX
    Explanations

    code with a particular emphasis on control flow elements

    oai_token-act-pair · gemini-2.0-flash

    say "break"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    queryInterface
    -0.83
    ContentAlignment
    -0.75
    :✨
    -0.74
    Referències
    -0.71
    İstinadlar
    -0.69
    zbęd
    -0.69
    nhung
    -0.68
    SequentialGroup
    -0.68
    BibitemShut
    -0.67
    клопе
    -0.65
    POSITIVE LOGITS
    br
    0.60
    pa
    0.57
    min
    0.54
    rd
    0.51
    ku
    0.50
    dr
    0.48
    6
    0.47
    iv
    0.47
    سا
    0.47
    db
    0.46
    Activations Density 3.751%

    No Known Activations