© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10993
    Prev
    Next
    INDEX
    Explanations

    the word "to" and common conjunctions and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    Expressing changes/transformations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     beginnetje
    -0.87
    featureID
    -0.86
    FunctionFlags
    -0.83
    FormTagHelper
    -0.82
    AlterField
    -0.82
    DockStyle
    -0.82
    complexContent
    -0.77
     autorytatywna
    -0.75
     '{@
    -0.74
    ();)
    -0.73
    POSITIVE LOGITS
     something
    2.83
    something
    2.55
    Something
    2.45
     Something
    2.41
     SOMETHING
    1.94
     qualcosa
    1.77
     somethin
    1.73
     algo
    1.59
     iets
    1.49
     quelque
    1.48
    Activations Density 1.661%

    No Known Activations