© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9311
    Prev
    Next
    INDEX
    Explanations

    words related to visual depictions, especially images and photographs

    oai_token-act-pair · gemini-2.0-flash

    visual depictions

    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
     оригіналу
    -0.66
    ATTEN
    -0.54
    getDoctrine
    -0.54
    дравству
    -0.53
     rêves
    -0.53
    attva
    -0.53
     cesse
    -0.52
    CodeAttribute
    -0.52
     gré
    -0.52
    ustomed
    -0.52
    POSITIVE LOGITS
    <bos>
    1.27
     pictures
    0.86
     image
    0.84
     picture
    0.83
     images
    0.80
     photograph
    0.74
     photographs
    0.72
     Pictures
    0.72
     photos
    0.71
     Images
    0.71
    Activations Density 0.978%

    No Known Activations