© 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. 13127
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "wind" and related concepts like wind power or turbines

    oai_token-act-pair · gemini-2.0-flash

    the concept of wind energy

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

    wind

    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
    reactstrap
    -0.48
    adə
    -0.46
    MigrationBuilder
    -0.44
     dima
    -0.44
    iorgio
    -0.43
    рак
    -0.43
    LN
    -0.43
    casus
    -0.42
     nhật
    -0.42
    ldt
    -0.41
    POSITIVE LOGITS
     مشين
    0.82
    TemporalType
    0.69
     */;
    0.67
    InitVars
    0.67
    ])/
    0.66
    WebServlet
    0.65
     Fø
    0.65
    ]))
    0.63
    setupUi
    0.62
    ]='\
    0.62
    Activations Density 0.546%

    No Known Activations