© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15851
    Prev
    Next
    INDEX
    Explanations

    mentions of tables, figures, equations and numerical results

    oai_token-act-pair · gemini-2.0-flash

    Data tables and reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     <=",
    -0.57
    ollectionView
    -0.53
     onCancelled
    -0.52
     Paused
    -0.49
    IndentedString
    -0.49
    ществует
    -0.49
    солю
    -0.48
    TacToe
    -0.48
     Tables
    -0.47
    \|\
    -0.47
    POSITIVE LOGITS
    SpringBootTest
    0.70
    LayoutConstraint
    0.60
    UseVisualStyle
    0.59
     HasFactory
    0.58
    skosten
    0.57
     textStatus
    0.56
    انظر
    0.56
    Према
    0.52
     miscellaneous
    0.52
    かって
    0.52
    Activations Density 28.540%

    No Known Activations