© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11263
    Prev
    Next
    INDEX
    Explanations

    contact information, specifically names, titles from a news organization, the word "Times", phone numbers, and email addresses

    oai_token-act-pair · gemini-2.0-flash

    writers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    IsMutable
    -0.41
    <bos>
    -0.33
     outside
    -0.32
    '
    -0.32
     after
    -0.31
     to
    -0.31
     mixed
    -0.31
     given
    -0.31
     сом
    -0.31
     last
    -0.31
    POSITIVE LOGITS
    Personendaten
    1.04
    
    0.86
    ########.
    0.83
    :+:
    0.79
    +:+
    0.77
    Kaynakça
    0.77
    ModelSerializer
    0.76
    StructEnd
    0.76
    SerializedSize
    0.75
    AutoScale
    0.75
    Activations Density 0.485%

    No Known Activations