© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14050
    Prev
    Next
    INDEX
    Explanations

    negations, possibilities, necessities, and contrasts

    oai_token-act-pair · gemini-2.0-flash

    Negations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Too
    -0.66
    Too
    -0.61
     too
    -0.60
     pinulongan
    -0.54
     TOO
    -0.51
    too
    -0.51
    PerformLayout
    -0.49
    Démographie
    -0.47
    XmlType
    -0.46
    cloudflare
    -0.46
    POSITIVE LOGITS
    expandindo
    0.66
     estimés
    0.64
     poffe
    0.59
    ypeł
    0.58
     noDo
    0.57
     StatefulWidget
    0.57
    叶凌天
    0.57
     Familienname
    0.57
     Оно
    0.56
    ///</
    0.56
    Activations Density 2.725%

    No Known Activations