© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3110
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate a context or setting.

    oai_token-act-pair · gemini-2.0-flash

    work/location/situation

    np_max-act · gemini-2.0-flash

    ground

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
    storm
    -1.06
    ground
    -0.98
    point
    -0.97
    storms
    -0.95
    finding
    -0.94
    waves
    -0.94
    flows
    -0.93
    writing
    -0.93
    wave
    -0.92
    writer
    -0.91
    POSITIVE LOGITS
    that
    0.80
    from
    0.70
     colorés
    0.69
     extérieures
    0.69
    OF
    0.68
    of
    0.68
     pianta
    0.67
     supérieures
    0.66
     disparu
    0.66
    for
    0.66
    Activations Density 5.552%

    No Known Activations