© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11564
    Prev
    Next
    INDEX
    Explanations

    words associated with time, studies, government, amounts, positions, or consequences

    oai_token-act-pair · gemini-2.0-flash

    month, week

    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
     months
    -0.79
    month
    -0.66
     Months
    -0.66
    Months
    -0.66
     maanden
    -0.62
     mesi
    -0.60
     month
    -0.60
    months
    -0.59
     meses
    -0.59
     MONTHS
    -0.55
    POSITIVE LOGITS
    StoryboardSegue
    0.98
    ^(@)
    0.83
     Jefus
    0.76
     MainAxisSize
    0.76
     itſelf
    0.75
    argout
    0.72
    sproz
    0.69
     Monfieur
    0.69
     myſelf
    0.69
    uxxxx
    0.69
    Activations Density 19.495%

    No Known Activations