© 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. 6568
    Prev
    Next
    INDEX
    Explanations

    terms related to official procedures, especially legal and technical.

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    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
     abiertos
    -0.50
     aperta
    -0.49
     abiertas
    -0.49
     aperto
    -0.49
     abierta
    -0.48
    Tried
    -0.47
     tried
    -0.46
     rendent
    -0.43
     scienza
    -0.41
     ouverts
    -0.41
    POSITIVE LOGITS
     InputDecoration
    0.72
     Савезне
    0.71
    ^(@)
    0.70
     podjela
    0.68
    saraba
    0.66
    IonicModule
    0.66
     itſelf
    0.65
     UIFont
    0.65
    insee
    0.63
    enumi
    0.62
    Activations Density 9.927%

    No Known Activations