© 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. 9043
    Prev
    Next
    INDEX
    Explanations

    youtube video links, but it also finds a lot of mathematical symbols that could be from URL parameters or from mathematical discussion

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    code and math snippets

    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
    دانشنامهٔ
    -0.82
     становника
    -0.71
     ExecuteAsync
    -0.59
    OGND
    -0.57
    <?>>
    -0.55
     disambiguazione
    -0.54
     typelib
    -0.54
    Sucesor
    -0.53
    Subview
    -0.53
    脚注の使い方
    -0.52
    POSITIVE LOGITS
    WebControls
    0.59
     M
    0.56
     QtWidgets
    0.54
    M
    0.51
    I
    0.51
     getApp
    0.50
     Roskov
    0.49
     I
    0.49
    cze
    0.47
    ibatis
    0.46
    Activations Density 2.138%

    No Known Activations