© 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. 15761
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to motorsports and motorcycles

    oai_token-act-pair · gemini-2.0-flash

    rider

    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
     الحره
    -0.63
    ResumeLayout
    -0.59
    łod
    -0.53
    gonic
    -0.52
     samochod
    -0.52
     samochód
    -0.51
    Erstellt
    -0.51
     coche
    -0.50
    undam
    -0.50
    irent
    -0.49
    POSITIVE LOGITS
     rider
    0.85
     riders
    0.85
     disambiguazione
    0.82
     ridden
    0.81
     riding
    0.80
    Rider
    0.76
     Rider
    0.75
     Riders
    0.75
     Riding
    0.73
    Riding
    0.71
    Activations Density 1.317%

    No Known Activations