© 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. 13513
    Prev
    Next
    INDEX
    Explanations

    terms related to software licenses and legal disclaimers, especially those involving terms of agreement, copyright, liability, or warranty.

    oai_token-act-pair · gemini-2.0-flash

    Software license/error messages

    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
     or
    -2.42
     или
    -1.62
    或
    -1.28
     nor
    -1.23
     atau
    -1.20
     یا
    -1.20
    หรือ
    -1.20
     nebo
    -1.18
     या
    -1.18
    거나
    -1.16
    POSITIVE LOGITS
     مشين
    0.76
    nologue
    0.73
     noqa
    0.73
     BIBSYS
    0.72
    CloseOperation
    0.72
     autorytatywna
    0.71
    putnik
    0.71
    IntoConstraints
    0.71
    AdapterFactory
    0.71
    TagMode
    0.70
    Activations Density 1.716%

    No Known Activations