Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14911
    Prev
    Next
    INDEX
    Explanations

    words that express an opinion or judgement but sometimes also highlights legal terminology and phrases

    oai_token-act-pair · gemini-2.0-flash

    transition words

    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
     kasarigan
    -0.97
    Portail
    -0.90
    ########.
    -0.87
    rungsseite
    -0.85
    Portale
    -0.79
    AccessorTable
    -0.77
    日閲覧
    -0.77
    Personensuche
    -0.75
     lenker
    -0.75
    Przypisy
    -0.73
    POSITIVE LOGITS
    OptionsMenu
    0.47
     imageNamed
    0.45
     veld
    0.43
    ^
    0.43
    ходи
    0.43
    xlarge
    0.41
     ř
    0.40
     Gra
    0.40
    _
    0.40
     e
    0.40
    Activations Density 1.251%

    No Known Activations