© 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. 5401
    Prev
    Next
    INDEX
    Explanations

    This neuron finds specific formatting codes and adjacent words like "pairs" and "details."

    oai_token-act-pair · gemini-2.0-flash

    variations of "off"

    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
    الإنجليزية
    -0.74
    BeginContext
    -0.65
     of
    -0.65
    EndInit
    -0.62
     esterni
    -0.59
    ⓧ
    -0.59
     AssemblyCulture
    -0.57
    GEBURTSDATUM
    -0.56
    UserScript
    -0.56
    Ծանոթ
    -0.56
    POSITIVE LOGITS
     off
    1.40
     Off
    1.06
    off
    0.99
     OFF
    0.96
    Off
    0.93
    OFF
    0.81
    オフ
    0.71
    offs
    0.69
     オフ
    0.69
    offsetof
    0.65
    Activations Density 0.643%

    No Known Activations