© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9251
    Prev
    Next
    INDEX
    Explanations

    a combination of numbers and capital letters, sometimes in the context of scientific or economic data

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     fug
    -0.52
     mustache
    -0.46
    arg
    -0.46
    lography
    -0.46
    kel
    -0.44
     cre
    -0.43
    odu
    -0.43
    lico
    -0.43
    寡
    -0.43
    shar
    -0.43
    POSITIVE LOGITS
    findpost
    0.98
    ftagPool
    0.82
    Personensuche
    0.81
     mourut
    0.76
    ScopeManager
    0.73
     betweenstory
    0.73
    SequentialGroup
    0.72
     autorytatywna
    0.70
     elettrica
    0.70
     skolen
    0.68
    Activations Density 2.607%

    No Known Activations