© 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. 13567
    Prev
    Next
    INDEX
    Explanations

    language indicating an endorsement of something which the author is writing about

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

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

    news article

    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
    EndGlobalSection
    -0.68
     createSlice
    -0.65
     frukt
    -0.50
    ChildIndex
    -0.48
    elemField
    -0.47
    المكان
    -0.45
    ゴリー
    -0.44
    ginfo
    -0.43
    ItemBackground
    -0.43
     traffico
    -0.43
    POSITIVE LOGITS
    :+:
    0.78
     estekak
    0.73
    OGND
    0.65
     وتسجيلات
    0.62
    GOTREF
    0.62
     AttributeSet
    0.60
    ⓧ
    0.59
    interopRequire
    0.58
    phosa
    0.57
    MigrationBuilder
    0.55
    Activations Density 1.436%

    No Known Activations