© 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. 10137
    Prev
    Next
    INDEX
    Explanations

    capital letters, especially H, T, J, O, Q, and C.

    oai_token-act-pair · gemini-2.0-flash

    J

    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
    <bos>
    -1.22
     defaultstate
    -0.63
    liferay
    -0.60
     initComponents
    -0.60
    urlencoded
    -0.58
    ymce
    -0.58
    enumi
    -0.56
     
    -0.55
     ThemeData
    -0.55
     свер
    -0.54
    POSITIVE LOGITS
     getB
    0.75
    RegistryLite
    0.75
     getP
    0.71
     getM
    0.69
    Grüsse
    0.66
    Còn
    0.64
     getF
    0.64
     resourceCulture
    0.62
     beroep
    0.61
    AÇÃO
    0.60
    Activations Density 2.189%

    No Known Activations