© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14077
    Prev
    Next
    INDEX
    Explanations

    words relating to business, finances and social issues.

    oai_token-act-pair · gemini-2.0-flash

    social, political, business context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     firent
    -0.50
     nôtre
    -0.49
     difficiles
    -0.48
     étages
    -0.48
     fumée
    -0.47
     lunghezza
    -0.46
     verksamhet
    -0.46
     appuy
    -0.46
     rayures
    -0.46
     början
    -0.46
    POSITIVE LOGITS
    Datuak
    0.96
    nonatomic
    0.92
    GEBURTSDATUM
    0.89
    :+:
    0.84
    ensement
    0.84
    SourceChecksum
    0.82
     تضيفلها
    0.81
     تانيه
    0.80
    crollView
    0.79
     SIMBAD
    0.79
    Activations Density 2.872%

    No Known Activations