© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10306
    Prev
    Next
    INDEX
    Explanations

    car manufacturers, models, and racing-related terms

    oai_token-act-pair · gemini-2.0-flash

    cars and vehicles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ControllerBase
    -0.65
     Vikipedi
    -0.62
    ARROLL
    -0.58
    RELATIVE
    -0.52
     sanitarios
    -0.52
     gesteld
    -0.52
     hueso
    -0.51
    Composable
    -0.51
     referrerpolicy
    -0.49
    Crossref
    -0.48
    POSITIVE LOGITS
    <bos>
    0.94
     oprot
    0.66
    SourceChecksum
    0.61
    ProcessEvent
    0.55
    cookieParser
    0.54
     WRX
    0.53
    Porsche
    0.53
    AntiForgeryToken
    0.52
     rallying
    0.51
     Савезне
    0.51
    Activations Density 0.296%

    No Known Activations