© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11253
    Prev
    Next
    INDEX
    Explanations

    mentions of Formula 1 or other car races and their participants

    oai_token-act-pair · gemini-2.0-flash

    racing/motorsports

    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
    kmäler
    -0.47
    ase
    -0.47
     track
    -0.46
    KEYCODE
    -0.45
     Car
    -0.45
    "}")
    -0.44
    atory
    -0.44
    ntz
    -0.43
    ResumeLayout
    -0.43
    min
    -0.43
    POSITIVE LOGITS
     pleaſure
    0.75
    ftagPool
    0.73
     poffible
    0.71
     myſelf
    0.71
     purpoſe
    0.65
     Савезне
    0.64
     Monfieur
    0.63
     fubject
    0.63
     AttributeSet
    0.62
    참고
    0.62
    Activations Density 0.852%

    No Known Activations