© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10720
    Prev
    Next
    INDEX
    Explanations

    forms of the word "bother" along with instances of the word "get" and adverbs ending in "ly."

    oai_token-act-pair · gemini-2.0-flash

    bother

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     hiér
    -0.57
    ')")
    -0.56
     useParams
    -0.53
    unile
    -0.52
     Driven
    -0.51
     Redu
    -0.50
    InitVars
    -0.50
    ешься
    -0.49
     réduction
    -0.49
    宛
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.73
     nahilalakip
    0.73
    χρι
    0.64
    principalColumn
    0.63
    ExtendWith
    0.60
     EconPapers
    0.60
     menjel
    0.59
    standig
    0.59
     @"/
    0.57
    XmlEnum
    0.57
    Activations Density 1.131%

    No Known Activations