© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12442
    Prev
    Next
    INDEX
    Explanations

    words related to a variety of loosely related topics, including downloads of things, baby diapers, computer programming issues, and taking a break at work.

    oai_token-act-pair · gemini-2.0-flash

    often

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Twice
    -0.92
    Twice
    -0.83
    twice
    -0.82
     twice
    -0.75
    ValueStyle
    -0.69
     Roskov
    -0.66
    MigrationBuilder
    -0.65
    DockStyle
    -0.60
     repeated
    -0.60
    済み
    -0.57
    POSITIVE LOGITS
     often
    2.22
     Often
    1.84
    often
    1.76
    Often
    1.73
     spesso
    1.48
     souvent
    1.45
     często
    1.23
     často
    1.20
     oft
    1.20
     vaak
    1.20
    Activations Density 5.339%

    No Known Activations