© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13644
    Prev
    Next
    INDEX
    Explanations

    the word "token" alongside words describing its use in Slack applications

    oai_token-act-pair · 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
     up
    -0.54
    лект
    -0.53
    mett
    -0.45
    asted
    -0.45
    conian
    -0.44
    kast
    -0.44
    SetString
    -0.44
     antem
    -0.44
    EDING
    -0.43
    vailability
    -0.43
    POSITIVE LOGITS
    bootstrapcdn
    0.78
    NameInMap
    0.72
     Autorizaciones
    0.67
     pinulongan
    0.63
    ंदीखरीदारी
    0.61
     otomatig
    0.60
    findpost
    0.60
    LookAnd
    0.59
    PreferredItem
    0.57
    ِّف
    0.57
    Activations Density 1.694%

    No Known Activations