© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude in advance for help, advice, or thanks

    oai_token-act-pair · gemini-2.0-flash

    Expressing gratitude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ⓧ
    -0.70
    TagMode
    -0.59
    ValueStyle
    -0.58
    клопе
    -0.57
    AddHtmlAttribute
    -0.57
    ScopeManager
    -0.57
    SourceChecksum
    -0.57
    yargs
    -0.57
    TargetException
    -0.52
    sidemargin
    -0.52
    POSITIVE LOGITS
     advance
    2.58
     ahead
    2.22
    advance
    2.17
     Advance
    2.08
    Advance
    1.99
     ADVANCE
    1.87
     Ahead
    1.85
    ahead
    1.83
     AHEAD
    1.80
    avance
    1.75
    Activations Density 1.766%

    No Known Activations