© 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. 8966
    Prev
    Next
    INDEX
    Explanations

    the neuron looks for code snippets and date and time references.

    oai_token-act-pair · gemini-2.0-flash

    programming or code syntax elements

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

    code and file paths

    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
    ChildScrollView
    -0.81
    mybatisplus
    -0.74
     insuffisamment
    -0.70
     оригіналу
    -0.70
    wpi
    -0.68
     GenerationType
    -0.66
    upol
    -0.66
     Bioaccumulative
    -0.65
     Вікіпе
    -0.64
    Hentet
    -0.63
    POSITIVE LOGITS
    ~
    0.59
     खु
    0.56
     Log
    0.54
     log
    0.52
     setTitle
    0.48
    ～
    0.47
    َم
    0.47
    Projection
    0.46
    elsey
    0.46
     ~
    0.46
    Activations Density 8.358%

    No Known Activations