© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11553
    Prev
    Next
    INDEX
    Explanations

    words broadly related to visuals and perspectives and storytelling

    oai_token-act-pair · gemini-2.0-flash

    Image context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     picture
    -2.47
     pictures
    -2.38
     Picture
    -2.22
    picture
    -2.13
    Picture
    -2.08
     PICTURE
    -2.06
     Pictures
    -1.94
     images
    -1.94
     image
    -1.88
    Pictures
    -1.87
    POSITIVE LOGITS
    SuppressMessage
    0.59
    Rhestr
    0.57
    InjectAttribute
    0.53
    Vidite
    0.52
     كومونز
    0.52
    Rohy
    0.52
     &___
    0.50
    Билгалдахарш
    0.50
    __]
    0.49
     AssemblyTitle
    0.48
    Activations Density 1.745%

    No Known Activations