© 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. 9092
    Prev
    Next
    INDEX
    Explanations

    Java main methods

    oai_token-act-pair · gemini-2.0-flash

    function argument patterns in code

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

    arg/args

    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
     '\\;'
    -0.69
    Gön
    -0.59
    følgelig
    -0.56
    DockStyle
    -0.56
    theless
    -0.52
    %</
    -0.52
     utafitiHapana
    -0.52
     δὲ
    -0.51
    Rüyada
    -0.50
     course
    -0.50
    POSITIVE LOGITS
    abestanden
    0.52
    AndEndTag
    0.48
    ExecuteReader
    0.48
     nase
    0.47
    WriteBarrier
    0.46
    NewUrlParser
    0.46
    watch
    0.45
    Watch
    0.44
     по
    0.44
     miras
    0.44
    Activations Density 3.548%

    No Known Activations