© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15392
    Prev
    Next
    INDEX
    Explanations

    mentions of various systems, policies, methods, and related processes.

    oai_token-act-pair · gemini-2.0-flash

    systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GEBURTSDATUM
    -0.88
     cherchés
    -0.87
    FontOfSize
    -0.80
    invokeLater
    -0.79
     Administrativna
    -0.76
     strategies
    -0.75
    RepeatedField
    -0.75
     estekak
    -0.74
    
    -0.74
     мәкал
    -0.73
    POSITIVE LOGITS
     variant
    0.53
     second
    0.53
    Ещё
    0.52
     poichè
    0.50
    ittoria
    0.49
     οποίο
    0.49
    ély
    0.49
    Variante
    0.48
    läufig
    0.48
    esticides
    0.48
    Activations Density 1.652%

    No Known Activations