© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14408
    Prev
    Next
    INDEX
    Explanations

    references to the immediate family

    oai_token-act-pair · gemini-2.0-flash

    parents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     acorns
    -0.75
     Rohing
    -0.64
     Hond
    -0.63
     XCTest
    -0.63
     mcqueen
    -0.62
    KommentareTeilen
    -0.62
    RATIO
    -0.61
    )\}
    -0.60
    ']>;
    -0.60
     Sph
    -0.60
    POSITIVE LOGITS
    __":
    0.56
     off
    0.54
    __':
    0.52
    ndham
    0.52
     General
    0.50
    bodyParser
    0.49
    <bos>
    0.48
     bowiem
    0.48
    不大
    0.47
     la
    0.47
    Activations Density 0.275%

    No Known Activations