© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2284
    Prev
    Next
    INDEX
    Explanations

    code snippets and variable names, particularly those possibly related to web servers or .NET

    oai_token-act-pair · gemini-2.0-flash

    Source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    MENAFN
    -0.66
    onViewCreated
    -0.60
    tagext
    -0.59
     Púb
    -0.58
    ########.
    -0.58
    larım
    -0.57
     händer
    -0.56
     nastro
    -0.56
     parís
    -0.54
     marrone
    -0.54
    POSITIVE LOGITS
    ourke
    0.82
    criminator
    0.68
    UTERS
    0.66
    ieteur
    0.66
     Ayer
    0.65
    glise
    0.64
    zerland
    0.63
    onsense
    0.63
    ICOLON
    0.61
    lgari
    0.61
    Activations Density 0.715%

    No Known Activations