© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15787
    Prev
    Next
    INDEX
    Explanations

    words associated with numbers, finance and government

    oai_token-act-pair · gemini-2.0-flash

    formal/descriptive/research writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    featureID
    -0.46
     question
    -0.45
     destes
    -0.43
    FieldDescriptor
    -0.43
     kaynağından
    -0.43
    Geplaatst
    -0.42
     approach
    -0.41
     قول
    -0.40
    Demografie
    -0.39
     questione
    -0.39
    POSITIVE LOGITS
     gyhoeddwyd
    0.71
    WithIOException
    0.70
    SpringRunner
    0.69
    XmlAccessType
    0.65
    PhysRev
    0.63
     amitié
    0.61
    CompleteListener
    0.61
    PerformLayout
    0.61
    AnimationsModule
    0.59
    ArrowToggle
    0.59
    Activations Density 9.410%

    No Known Activations