© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2059
    Prev
    Next
    INDEX
    Explanations

    text seemingly derived from some kind of religious document or sermon

    oai_token-act-pair · gemini-2.0-flash

    Code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     estimés
    -0.48
    出版年
    -0.47
    makeConstraints
    -0.46
    epiece
    -0.44
    Personendaten
    -0.44
    canestro
    -0.44
    קישורים
    -0.43
     chua
    -0.43
     ujednoznacz
    -0.43
     raw
    -0.42
    POSITIVE LOGITS
    ScopeManager
    0.67
    ValueStyle
    0.63
    ąp
    0.62
    iconque
    0.56
    yntaxException
    0.56
     tráng
    0.55
    engertian
    0.55
    complexContent
    0.55
    ύτε
    0.54
    poor
    0.54
    Activations Density 16.792%

    No Known Activations