© 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. 11595
    Prev
    Next
    INDEX
    Explanations

    a complex combination of common words and phrases suggesting it may be recognizing clauses.

    oai_token-act-pair · gemini-2.0-flash

    Positive adjectives

    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
     GenerationType
    -0.94
     kasarigan
    -0.63
    OGND
    -0.62
    日閲覧
    -0.57
    حوال
    -0.54
    MigrationBuilder
    -0.54
    FormTagHelper
    -0.54
     mendatang
    -0.52
     referrerpolicy
    -0.51
     المعيارى
    -0.51
    POSITIVE LOGITS
     perfectly
    1.24
     good
    1.12
     healthy
    1.04
     decent
    1.03
    perfectly
    0.96
    good
    0.94
     nice
    0.93
     wholesome
    0.92
     respectable
    0.91
     legitimate
    0.90
    Activations Density 3.380%

    No Known Activations