© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7127
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to capturing screenshots or images from a screen, along with some related terms like "internet", "mode", and "copy", often in the context of technical descriptions or instructions.

    oai_token-act-pair · gemini-2.0-flash

    saving screenshots

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     calldata
    -0.66
    SequentialGroup
    -0.65
     CreateTagHelper
    -0.56
    StructEnd
    -0.55
    ̈́
    -0.52
     للاسماء
    -0.49
    IntoConstraints
    -0.49
     VizieR
    -0.49
    tagHelperRunner
    -0.48
    ūsu
    -0.48
    POSITIVE LOGITS
    save
    0.77
     Save
    0.76
     save
    0.74
     Screenshot
    0.72
    Save
    0.71
     screenshot
    0.71
     photographing
    0.69
     photographed
    0.68
     saved
    0.68
     saving
    0.68
    Activations Density 1.848%

    No Known Activations