© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10411
    Prev
    Next
    INDEX
    Explanations

    car brands and models

    oai_token-act-pair · gemini-2.0-flash

    Peugeot cars

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     unknownFields
    -0.63
    UnsafeEnabled
    -0.61
    Coordonnées
    -0.54
     désolés
    -0.54
    hips
    -0.52
    PerformLayout
    -0.51
     protoimpl
    -0.51
    sement
    -0.51
     ivelany
    -0.50
     Wiktionnaire
    -0.49
    POSITIVE LOGITS
    
    0.57
    posedge
    0.49
    argb
    0.49
    ROUTINE
    0.47
    Newswire
    0.47
    plyr
    0.45
    язы
    0.45
    gettext
    0.45
    strix
    0.45
    Greater
    0.45
    Activations Density 0.195%

    No Known Activations