© 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. 13008
    Prev
    Next
    INDEX
    Explanations

    LaTeX code or Rust code

    oai_token-act-pair · gemini-2.0-flash

    tokens related to textual data or specific formatting

    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
     cherchés
    -0.65
    GOTREF
    -0.64
     estekak
    -0.63
     betweenstory
    -0.62
    migrationBuilder
    -0.60
    InputBorder
    -0.59
    دانشنامهٔ
    -0.59
     GenerationType
    -0.58
    orianCalendar
    -0.58
    featureID
    -0.56
    POSITIVE LOGITS
    iyle
    0.52
    xide
    0.52
     six
    0.50
    อย่างไร
    0.50
    威廉
    0.47
    orra
    0.46
     اسک
    0.45
     there
    0.45
     coû
    0.45
     наи
    0.45
    Activations Density 0.085%

    No Known Activations