© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    discourse in legal or technical documents

    oai_token-act-pair · gemini-2.0-flash

    construction and changes

    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
    DrawerToggle
    -0.51
    jsxFileName
    -0.51
    etje
    -0.50
     gql
    -0.48
    ély
    -0.48
     Poitiers
    -0.47
    NSFW
    -0.46
     ſtate
    -0.46
    Espèce
    -0.45
     fubject
    -0.45
    POSITIVE LOGITS
    ida
    0.63
     MainAxisSize
    0.61
    actionMode
    0.60
     didat
    0.59
    /**
    0.59
    Климат
    0.58
    power
    0.57
     power
    0.57
    IDA
    0.56
    //
    0.56
    Activations Density 3.054%

    No Known Activations