© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3221
    Prev
    Next
    INDEX
    Explanations

    technical writing that describes how something works.

    oai_token-act-pair · gemini-2.0-flash

    automatic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     regia
    -0.49
    lardır
    -0.47
    wijs
    -0.41
    нца
    -0.41
    ViewStyle
    -0.41
    хо
    -0.41
     pły
    -0.40
     Darfur
    -0.40
     saudável
    -0.40
     kuchen
    -0.39
    POSITIVE LOGITS
     automatic
    2.19
     automatically
    2.00
     Automatic
    1.98
    automatic
    1.97
     automated
    1.96
     auto
    1.95
    Automatic
    1.89
     automat
    1.87
     AUTO
    1.81
     AUTOMATIC
    1.80
    Activations Density 5.412%

    No Known Activations