© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15754
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to images and visual media

    oai_token-act-pair · gemini-2.0-flash

    picture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ScopeManager
    -0.63
     مشين
    -0.58
    Xna
    -0.55
    DockStyle
    -0.52
    createStatement
    -0.51
     slutt
    -0.50
    jstor
    -0.49
     actionPerformed
    -0.49
    Frosty
    -0.48
     geldig
    -0.48
    POSITIVE LOGITS
    FormTagHelper
    0.59
    itaries
    0.57
    schon
    0.56
    openConnection
    0.53
    UserScript
    0.52
     photographed
    0.50
    GRAT
    0.48
    gebnis
    0.48
    kiss
    0.47
    Personensuche
    0.47
    Activations Density 1.389%

    No Known Activations