© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1482
    Prev
    Next
    INDEX
    Explanations

    the word "image" in various contexts

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Hentet
    -0.69
     typelib
    -0.68
     Paglinawan
    -0.66
    ImageContext
    -0.66
     ―――――
    -0.63
     Архиви
    -0.63
    ymal
    -0.61
    WebVitals
    -0.60
    dibles
    -0.60
     Numerade
    -0.60
    POSITIVE LOGITS
    からです
    0.50
     fore
    0.42
    toxic
    0.40
     μέ
    0.40
     файлы
    0.39
     @
    0.37
     name
    0.37
     arché
    0.37
    (@
    0.36
     aseg
    0.36
    Activations Density 8.095%

    No Known Activations