© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 368
    Prev
    Next
    INDEX
    Explanations

    placenames and some other proper nouns

    oai_token-act-pair · gemini-2.0-flash

    rivers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     незавершена
    -1.12
    contentLoaded
    -0.94
    GEBURTSDATUM
    -0.92
    ArrowToggle
    -0.90
    хьтан
    -0.90
     Meksiku
    -0.90
    Personensuche
    -0.87
     transférez
    -0.84
    Vidite
    -0.83
    parsedMessage
    -0.81
    POSITIVE LOGITS
    в
    0.48
    ритори
    0.47
    try
    0.46
    useState
    0.44
    yl
    0.43
     ageing
    0.42
     useState
    0.42
     personalised
    0.42
    heim
    0.42
     ols
    0.40
    Activations Density 7.100%

    No Known Activations