© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10260
    Prev
    Next
    INDEX
    Explanations

    table-like data containing numbers and some medical terminology

    oai_token-act-pair · gemini-2.0-flash

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    glGen
    -0.56
    planung
    -0.56
    帖最后由
    -0.55
     salon
    -0.52
     salons
    -0.52
    nfs
    -0.51
    ametro
    -0.51
     mout
    -0.50
     Poole
    -0.50
     kız
    -0.50
    POSITIVE LOGITS
    OrBuilder
    0.62
    parsedMessage
    0.61
    GEBURTSDATUM
    0.59
    DeleteBehavior
    0.57
    RTLD
    0.57
     localObject
    0.54
    RenderAtEndOf
    0.54
    RegressionTest
    0.54
     BoxDecoration
    0.53
    aarrggbb
    0.53
    Activations Density 1.080%

    No Known Activations