© 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. 7792
    Prev
    Next
    INDEX
    Explanations

    the word "hub" and words related to geographic origins

    oai_token-act-pair · gemini-2.0-flash

    hub

    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
    niająca
    -0.66
     nélk
    -0.65
     nélkül
    -0.65
     revés
    -0.64
     jegy
    -0.64
    eraard
    -0.64
     poussière
    -0.63
     abroad
    -0.63
    arbeid
    -0.63
     emel
    -0.62
    POSITIVE LOGITS
     Courant
    0.65
     ViewHolder
    0.63
    SPATH
    0.62
    phazard
    0.62
    SuspendLayout
    0.62
    Capítulo
    0.61
     IEnumerator
    0.60
     Yom
    0.59
     Mares
    0.59
    YMMV
    0.58
    Activations Density 2.237%

    No Known Activations