© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11642
    Prev
    Next
    INDEX
    Explanations

    boolean values, particularly the word "true," sometimes alongside other related or numerical information.

    oai_token-act-pair · gemini-2.0-flash

    true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     true
    -0.53
    atorship
    -0.51
    󠁢
    -0.50
    hoea
    -0.50
    ólica
    -0.49
    átil
    -0.48
    lapsingToolbar
    -0.48
     pinulongan
    -0.48
     realising
    -0.47
    tyfik
    -0.47
    POSITIVE LOGITS
    protoimpl
    0.79
     برانيه
    0.54
     للاسماء
    0.52
    UnsafeEnabled
    0.52
     الحره
    0.52
    iddhar
    0.51
    Parcelize
    0.50
    املة
    0.50
    ConstraintMaker
    0.49
     autorytatywna
    0.49
    Activations Density 1.212%

    No Known Activations