© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11433
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to technical topics about computer systems, medicine, and business

    oai_token-act-pair · gemini-2.0-flash

    people and their interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ConstraintMaker
    -0.52
    eradish
    -0.46
     convertView
    -0.46
    omotor
    -0.46
    kosť
    -0.44
    ORNING
    -0.44
    PyExc
    -0.43
     others
    -0.43
    cinogenicity
    -0.43
     victims
    -0.42
    POSITIVE LOGITS
    <bos>
    1.20
    StoreMessageInfo
    0.70
    WebVitals
    0.65
     vostri
    0.63
    Portail
    0.59
    Билгалдахарш
    0.58
    saraba
    0.57
     vetores
    0.57
     confronti
    0.56
     {}));
    0.54
    Activations Density 3.213%

    No Known Activations