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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14639
    Prev
    Next
    INDEX
    Explanations

    the word "image" and terms associated with it

    oai_token-act-pair · gemini-2.0-flash

    image

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     image
    -2.41
    image
    -2.13
    Image
    -2.02
     Image
    -1.95
     images
    -1.95
     imagem
    -1.77
     imagen
    -1.76
     IMAGE
    -1.71
     Images
    -1.70
    IMAGE
    -1.68
    POSITIVE LOGITS
    MessageTagHelper
    0.77
    OGND
    0.73
    ftagPool
    0.71
    $.
    0.70
    TintMode
    0.69
     rospy
    0.69
    WireFormatLite
    0.69
    WriteTagHelper
    0.68
    exitRule
    0.68
     useAppContext
    0.68
    Activations Density 0.652%

    No Known Activations