© 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. 338
    Prev
    Next
    INDEX
    Explanations

    C++ code and comments

    oai_token-act-pair · gemini-2.0-flash

    asterisks

    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
     
    -0.41
    GeoNames
    -0.40
     den
    -0.40
    HomeController
    -0.40
     au
    -0.39
    قایناق‌لار
    -0.38
    યા
    -0.38
    chera
    -0.38
    cepan
    -0.38
     a
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.98
    GEBURTSDATUM
    0.90
     viewDidLoad
    0.89
     Италијани
    0.88
    Personensuche
    0.84
     مشين
    0.82
     myſelf
    0.76
    WriteTagHelper
    0.73
    RegistryLite
    0.73
    Enllaces
    0.70
    Activations Density 1.690%

    No Known Activations