© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1030
    Prev
    Next
    INDEX
    Explanations

    words that indicate organization names or descriptions, especially within the context of legal or official contexts

    oai_token-act-pair · gemini-2.0-flash

    Establishment/Devotion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     مرئيه
    -0.63
     jScrollPane
    -0.61
     NSCoder
    -0.60
     AppModule
    -0.59
     CURIAM
    -0.59
    ConstraintMaker
    -0.58
     cref
    -0.58
    enoord
    -0.57
    WebServlet
    -0.56
    ANTLR
    -0.54
    POSITIVE LOGITS
    AndEndTag
    0.73
    hdashline
    0.55
     متعلقه
    0.54
    Personendaten
    0.53
    HasForeignKey
    0.49
    cticut
    0.49
     kapturem
    0.48
    DockStyle
    0.48
     Öffentlichkeit
    0.48
    NUMX
    0.48
    Activations Density 19.572%

    No Known Activations