© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9047
    Prev
    Next
    INDEX
    Explanations

    positive adjectives modifying "way" and "solution", or "booster"

    oai_token-act-pair · gemini-2.0-flash

    Positive choice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Bourgoin
    -0.69
     كومونز
    -0.64
    Diweddarwch
    -0.57
    AnchorStyles
    -0.57
     zelve
    -0.56
     mariée
    -0.52
    hôpital
    -0.50
     للمعارف
    -0.50
     supérieurs
    -0.50
     marié
    -0.49
    POSITIVE LOGITS
     choice
    0.81
     choix
    0.73
     option
    0.70
     choices
    0.67
     way
    0.62
     vị
    0.60
     options
    0.60
     decision
    0.59
     candidate
    0.57
     replacement
    0.56
    Activations Density 1.138%

    No Known Activations