© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13500
    Prev
    Next
    INDEX
    Explanations

    lines of code that declare 'const' variables

    oai_token-act-pair · gemini-2.0-flash

    fragments of code or programming language syntax

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

    Code syntax

    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
     للاسماء
    -0.49
    الر
    -0.47
    MockMvc
    -0.47
     circulaire
    -0.45
    DisplayMode
    -0.45
     Hall
    -0.44
    UrlResolution
    -0.44
     zahrani
    -0.43
     امنیت
    -0.43
     desaparecer
    -0.41
    POSITIVE LOGITS
     propOrder
    0.72
     }}">
    0.65
    wieś
    0.63
     незавершена
    0.61
    PerformLayout
    0.61
    帖最后由
    0.60
    UserScript
    0.60
    RetentionPolicy
    0.60
    Hentet
    0.59
     MyBatis
    0.59
    Activations Density 10.719%

    No Known Activations