© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3832
    Prev
    Next
    INDEX
    Explanations

    mentions of amounts of things.

    oai_token-act-pair · 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
     الحره
    -0.50
    :],
    -0.46
     meanwhile
    -0.46
    +
    -0.44
     additionally
    -0.44
     >=",
    -0.44
    FAILURE
    -0.44
    :]:
    -0.43
     alternatively
    -0.41
    uaian
    -0.41
    POSITIVE LOGITS
    <bos>
    1.08
     $(\%)$
    0.65
    MigrationBuilder
    0.65
     (%)
    0.63
     proportion
    0.63
    bufio
    0.61
     itſelf
    0.59
    nosaurus
    0.58
    BrowserRouter
    0.57
    DockStyle
    0.57
    Activations Density 1.473%

    No Known Activations