© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5098
    Prev
    Next
    INDEX
    Explanations

    code snippets and Portuguese words.

    oai_token-act-pair · gemini-2.0-flash

    non-english code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    GEBURTSDATUM
    -0.79
    IUrlHelper
    -0.78
     Theſe
    -0.70
     Cabello
    -0.69
     <>",
    -0.68
     Italijanski
    -0.68
     ſta
    -0.67
     Monfieur
    -0.67
     snippetHide
    -0.66
     Efq
    -0.66
    POSITIVE LOGITS
     e
    0.42
    AndEndTag
    0.39
    UnsafeEnabled
    0.38
     ModelAndView
    0.38
     им
    0.36
    QMetaType
    0.35
    ordinaire
    0.35
     capito
    0.34
     صوتيه
    0.34
     ele
    0.33
    Activations Density 1.178%

    No Known Activations