© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14143
    Prev
    Next
    INDEX
    Explanations

    the words "holiday" or "holidays" and "sanctity", and one time it finds "tells"

    oai_token-act-pair · gemini-2.0-flash

    holiday

    np_max-act · gemini-2.0-flash

    holiday

    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
     indicates
    -0.70
     says
    -0.66
     suggests
    -0.60
     notes
    -0.59
     Notes
    -0.58
    Notes
    -0.56
    says
    -0.56
     explains
    -0.55
    Indicates
    -0.54
    Says
    -0.52
    POSITIVE LOGITS
    <bos>
    1.27
    HttpFoundation
    0.89
     ProtoMessage
    0.81
    WindowConstants
    0.80
     ThemeData
    0.77
    sizeCache
    0.77
    MemoryWarning
    0.77
    +:+
    0.76
     AssemblyProduct
    0.76
    istoitu
    0.75
    Activations Density 0.835%

    No Known Activations