© 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. 6237
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to science, engineering and document coding

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific contexts

    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
     easily
    -2.25
    easily
    -2.03
     Easily
    -1.98
     easy
    -1.78
    Easily
    -1.77
     facilmente
    -1.65
     fácilmente
    -1.61
    Easy
    -1.58
     facilement
    -1.56
     readily
    -1.55
    POSITIVE LOGITS
     nahilalakip
    0.54
    Verso
    0.50
     StatelessWidget
    0.50
    +#+
    0.49
    ForValue
    0.49
    resh
    0.49
    autorest
    0.49
    AddTagHelper
    0.48
    InjectAttribute
    0.47
     Heywood
    0.47
    Activations Density 3.198%

    No Known Activations