© 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. 287
    Prev
    Next
    INDEX
    Explanations

    information related to sports match outcomes

    oai_token-act-pair · gemini-2.0-flash

    winning streaks

    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
    ⓧ
    -0.81
     disfr
    -0.52
    tonode
    -0.51
    setViewportView
    -0.44
     ligação
    -0.43
    binaan
    -0.43
     Normdatei
    -0.43
    Geografi
    -0.43
    gdx
    -0.42
    ✷
    -0.40
    POSITIVE LOGITS
     BoxFit
    0.75
    NameInMap
    0.62
     Theſe
    0.59
     Niv
    0.59
     Heere
    0.58
    नलिखित
    0.57
    }{*}{
    0.57
    antung
    0.56
    emark
    0.56
    Клуб
    0.55
    Activations Density 0.457%

    No Known Activations