© 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. 10114
    Prev
    Next
    INDEX
    Explanations

    the word "to" preceded by a word suggesting purpose or ability

    oai_token-act-pair · gemini-2.0-flash

    tokens related to instruction or queries

    np_token-act-pair-logits · gpt-4o-mini
    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
    RenderAtEndOf
    -0.63
    RectangleBorder
    -0.63
    **
    -0.61
    abetes
    -0.59
    StoryboardSegue
    -0.57
    IMPORTED
    -0.56
    endphp
    -0.56
    __":
    -0.54
    "},
    -0.54
    Зноскі
    -0.53
    POSITIVE LOGITS
    OGND
    0.47
    Rahman
    0.47
     ***!
    0.47
    ThroughAttribute
    0.46
     validamos
    0.46
    بل
    0.46
    éraires
    0.45
    δ
    0.45
     ویکی‌پدیای
    0.45
     Hartford
    0.45
    Activations Density 3.059%

    No Known Activations