© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7264
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a telling of events.

    oai_token-act-pair · gemini-2.0-flash

    narratives

    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
     humaines
    -0.56
    TagMode
    -0.56
     незавершена
    -0.54
    RunWith
    -0.51
     Vikipedi
    -0.51
     folgen
    -0.49
    InputTagHelper
    -0.48
    styleType
    -0.48
    unknownFields
    -0.46
    Impossible
    -0.46
    POSITIVE LOGITS
    >{@
    0.68
    CloseOperation
    0.61
    parsedMessage
    0.60
    MigrationBuilder
    0.59
    =$?
    0.55
     للمعارف
    0.54
     مؤرشف
    0.52
    httphttps
    0.51
     PyQt
    0.50
    findpost
    0.50
    Activations Density 3.746%

    No Known Activations