© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 856
    Prev
    Next
    INDEX
    Explanations

    words related to video games, their design, or discussion of gameplay

    oai_token-act-pair · gemini-2.0-flash

    Software, games, and reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     okuyayım
    -0.57
     CanadaChoose
    -0.54
     szóci
    -0.52
    ніципалі
    -0.52
     sedia
    -0.50
     migli
    -0.50
     ouv
    -0.49
    Sucks
    -0.49
    reactstrap
    -0.49
     pesce
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.78
    MessageTagHelper
    0.66
     NSCoder
    0.56
     Kombat
    0.54
    WebServlet
    0.54
    tagHelperRunner
    0.52
    RAP
    0.51
     Voyager
    0.51
    AGE
    0.49
    age
    0.48
    Activations Density 10.162%

    No Known Activations