© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13513
    Prev
    Next
    INDEX
    Explanations

    email headers, court filings, and question/answer formats

    oai_token-act-pair · gemini-2.0-flash

    email and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     برانيه
    -0.53
    })`
    -0.52
    toos
    -0.48
    ")"
    -0.46
    ControllerAdvice
    -0.46
    XmlIgnore
    -0.46
    >");
    
    -0.45
    ^{+}\
    -0.44
     puissiez
    -0.44
    aguas
    -0.44
    POSITIVE LOGITS
    ↵↵↵↵
    1.22
    ↵↵↵
    1.16
    ↵↵↵↵↵
    1.12
    ↵↵↵↵↵↵
    1.11
    ↵↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵
    0.86
    ↵↵↵↵↵↵↵↵↵↵
    0.84
    ↵↵↵↵↵↵↵↵↵↵↵
    0.83
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.81
    Activations Density 3.997%

    No Known Activations