© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 293
    Prev
    Next
    INDEX
    Explanations

    words related to photography and possibly other forms of media capture

    oai_token-act-pair · gemini-2.0-flash

    photo

    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
    Negative Logits
     photo
    -2.23
     photos
    -2.19
     Photo
    -2.11
    Photo
    -2.05
     Photos
    -1.99
    Photos
    -1.98
    photo
    -1.94
     photographs
    -1.88
     photograph
    -1.85
     PHOTO
    -1.78
    POSITIVE LOGITS
    hasMoreElements
    0.51
    IntoConstraints
    0.51
     MainAxisSize
    0.50
    MessageTagHelper
    0.50
     население
    0.49
     Scribd
    0.47
     PLWABN
    0.46
    InvalidProtocol
    0.45
    GraphicsUnit
    0.44
    +:+
    0.43
    Activations Density 4.525%

    No Known Activations