© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15559
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be matching question prompts, conditional statements, and formatting tags such as <p>

    oai_token-act-pair · gemini-2.0-flash

    code and technical reports

    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
     ErrIntOverflow
    -0.47
    BagLayout
    -0.46
     rheinland
    -0.46
     सत्यापित
    -0.45
    WindowConstants
    -0.45
    icina
    -0.45
     complémentaires
    -0.45
    енера
    -0.45
    رحلة
    -0.45
     žiad
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.73
    WriteBarrier
    0.69
     CURIAM
    0.66
    клопе
    0.65
    PreferredItem
    0.65
     onOptions
    0.63
    HtmlAttribute
    0.62
    @[+][
    0.62
     endforeach
    0.60
    AndroidJUnit
    0.59
    Activations Density 0.146%

    No Known Activations