© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12810
    Prev
    Next
    INDEX
    Explanations

    negative descriptors or contrasts

    oai_token-act-pair · gemini-2.0-flash

    occupations

    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
     défendre
    -0.74
    Hochspringen
    -0.70
    OrBuilder
    -0.63
    onomía
    -0.61
    LLocation
    -0.60
     remercier
    -0.57
    AutoField
    -0.56
     détruire
    -0.56
    Coaching
    -0.56
     étrang
    -0.56
    POSITIVE LOGITS
     mover
    0.78
     builder
    0.75
     healer
    0.75
     communicator
    0.74
     recruiter
    0.74
     evaluator
    0.74
     importer
    0.71
     purchaser
    0.71
     organizer
    0.71
     negotiator
    0.71
    Activations Density 2.846%

    No Known Activations