© 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. 328
    Prev
    Next
    INDEX
    Explanations

    proper nouns including people and places

    oai_token-act-pair · gemini-2.0-flash

    Random assortment of comments

    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
    DataColumn
    -0.48
    StoryboardSegue
    -0.45
    printStackTrace
    -0.45
     Temple
    -0.44
    ölker
    -0.42
     Hal
    -0.41
     ._
    -0.40
    interopRequire
    -0.39
     ...
    -0.39
     hands
    -0.39
    POSITIVE LOGITS
    ftagPool
    0.71
     varandra
    0.70
    Дереккөздер
    0.67
     défauts
    0.67
     blessés
    0.65
     elkaar
    0.63
     inconvénients
    0.62
     pères
    0.61
     propriétés
    0.60
     sécher
    0.60
    Activations Density 2.914%

    No Known Activations