© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1653
    Prev
    Next
    INDEX
    Explanations

    positive, superlative, or comparative phrases

    oai_token-act-pair · gemini-2.0-flash

    new

    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
     new
    -0.59
    Multiple
    -0.45
     Multiple
    -0.45
     Another
    -0.43
    new
    -0.43
     multi
    -0.43
     multiple
    -0.42
    stot
    -0.40
     primary
    -0.40
     another
    -0.40
    POSITIVE LOGITS
     ostavi
    0.96
    +#+
    0.95
    脚注の使い方
    0.90
     financières
    0.84
     Мексичка
    0.84
     BoxFit
    0.83
    KommentareTeilen
    0.82
    MENAFN
    0.82
     saites
    0.81
     StatefulWidget
    0.81
    Activations Density 0.640%

    No Known Activations