© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7797
    Prev
    Next
    INDEX
    Explanations

    the word "oral"

    oai_token-act-pair · gemini-2.0-flash

    oral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -0.80
     and
    -0.75
     faptul
    -0.71
     
    -0.61
    <strong>
    -0.60
    .
    -0.60
     in
    -0.59
     to
    -0.57
     that
    -0.56
    2
    -0.54
    POSITIVE LOGITS
     betweenstory
    1.42
    rungsseite
    1.27
     disambiguazione
    1.23
     utafitiHapana
    1.22
     المعيارى
    1.18
     Мексичка
    1.14
     transférez
    1.05
     Roskov
    1.05
    EndGlobalSection
    1.05
     يتيمه
    1.03
    Activations Density 0.403%

    No Known Activations