© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11598
    Prev
    Next
    INDEX
    Explanations

    mentions of sections in research papers

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and programming concepts

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

    Scientific/technical papers

    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
    TypedDataSet
    -0.53
    ✨:
    -0.51
    لومات
    -0.50
    |}{}
    -0.50
    paksa
    -0.49
    forChild
    -0.49
     amorti
    -0.49
    ']->
    -0.47
    UrlResolution
    -0.47
     Inoue
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.79
    Revenir
    0.68
    новништво
    0.68
    MigrationBuilder
    0.66
    NameInMap
    0.60
     confronti
    0.60
     للاسماء
    0.57
    TabIndex
    0.54
    didSet
    0.54
     resourceCulture
    0.54
    Activations Density 4.425%

    No Known Activations