© 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. 15831
    Prev
    Next
    INDEX
    Explanations

    the letter "r" in code, data, or configuration files

    oai_token-act-pair · gemini-2.0-flash

    r

    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
    ect
    -0.68
    WireFormatLite
    -0.61
    ed
    -0.60
    easier
    -0.59
    ie
    -0.59
    ig
    -0.59
    ajara
    -0.58
    setVerticalGroup
    -0.58
    et
    -0.57
    ضى
    -0.57
    POSITIVE LOGITS
    URLException
    0.54
    WebServlet
    0.52
    AnimationsModule
    0.47
    phem
    0.46
    !("
    0.46
    newArrayList
    0.44
    NOVEMBER
    0.41
    قایناق‌لار
    0.41
     ErrIntOverflow
    0.41
     nifer
    0.41
    Activations Density 1.789%

    No Known Activations