© 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. 11867
    Prev
    Next
    INDEX
    Explanations

    LaTeX code, especially definitions and control sequences

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     jScrollPane
    -0.76
    يكب
    -0.65
     CURIAM
    -0.62
    Clik
    -0.50
    GUY
    -0.49
    ########.
    -0.49
    AndEndTag
    -0.48
    obre
    -0.47
    "";
    -0.47
     exogenous
    -0.47
    POSITIVE LOGITS
    terase
    0.71
    lgari
    0.64
    dotenv
    0.61
     AssemblyTitle
    0.59
     =
    0.59
    AccessorTable
    0.57
     AssemblyVersion
    0.54
    InsertCommand
    0.53
    UTERS
    0.53
    playable
    0.53
    Activations Density 2.648%

    No Known Activations