© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6642
    Prev
    Next
    INDEX
    Explanations

    the word "roof"

    oai_token-act-pair · gemini-2.0-flash

    roof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     roof
    -2.47
     Roof
    -2.11
    roof
    -1.98
    Roof
    -1.96
     ROOF
    -1.91
     roofs
    -1.83
     rooftop
    -1.52
     rooftops
    -1.40
     roofing
    -1.39
     ceiling
    -1.38
    POSITIVE LOGITS
    ValueStyle
    0.78
    <bos>
    0.64
    awtextra
    0.57
     pat
    0.56
    Pat
    0.55
     تضيفلها
    0.54
    Enllaces
    0.53
     Patch
    0.52
    érience
    0.52
    ethene
    0.51
    Activations Density 0.584%

    No Known Activations