© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12829
    Prev
    Next
    INDEX
    Explanations

    mentions of LED lights, vehicle wheels and size specifications

    oai_token-act-pair · gemini-2.0-flash

    car features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <bos>
    -0.65
    enumi
    -0.55
     Drapeau
    -0.49
    netbeans
    -0.48
    findOrFail
    -0.44
    rm
    -0.43
    pail
    -0.43
    IANGLES
    -0.43
    Cin
    -0.42
    情的
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.79
    UrlResolution
    0.79
    )");
    0.69
     EconPapers
    0.68
    锈钢
    0.67
     poffible
    0.66
     itſelf
    0.65
     pinulongan
    0.65
    Искәрмәләр
    0.65
     Italijanski
    0.63
    Activations Density 1.111%

    No Known Activations