© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4362
    Prev
    Next
    INDEX
    Explanations

    code snippets with a Java or C++ flavor

    oai_token-act-pair · gemini-2.0-flash

    space

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     surla
    -0.57
    writeField
    -0.51
    κτηρισ
    -0.47
    Poe
    -0.45
     Poc
    -0.44
     acost
    -0.43
    ########.
    -0.42
    ValueStyle
    -0.42
    новништво
    -0.42
     ports
    -0.41
    POSITIVE LOGITS
     space
    0.79
    SPACE
    0.68
     Space
    0.68
     utafitiHapana
    0.65
    Space
    0.65
     SPACE
    0.65
    WithIOException
    0.65
    space
    0.65
    空间
    0.62
     AssemblyCompany
    0.62
    Activations Density 0.627%

    No Known Activations