© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13442
    Prev
    Next
    INDEX
    Explanations

    words related to automobile towing and repair

    oai_token-act-pair · gemini-2.0-flash

    Towing

    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
     preſent
    -0.65
     purpoſe
    -0.64
     itſelf
    -0.62
     Theſe
    -0.62
     transférez
    -0.60
     uſe
    -0.60
    fillType
    -0.59
     moſt
    -0.59
     Jefus
    -0.59
     nawr
    -0.58
    POSITIVE LOGITS
     tow
    0.98
     towed
    0.78
     Tow
    0.70
     towing
    0.68
    tow
    0.67
     TOW
    0.67
    Tow
    0.66
     Towing
    0.50
     ref
    0.50
     abgesch
    0.49
    Activations Density 0.772%

    No Known Activations