© 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. 6435
    Prev
    Next
    INDEX
    Explanations

    words and phrases that amplify meaning or indicate degree, like "very", "most," or comparatives.

    oai_token-act-pair · gemini-2.0-flash

    Degree or frequency

    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
    ponses
    -0.51
     muualla
    -0.51
     lät
    -0.47
    InputBorder
    -0.45
     pleaf
    -0.45
    EndInit
    -0.44
    చు
    -0.44
    },{
    -0.43
    TestTools
    -0.43
     Causeway
    -0.43
    POSITIVE LOGITS
    aarrggbb
    0.69
    rrggbb
    0.58
    elemField
    0.54
    وردار
    0.53
     feed
    0.53
    Collegamenti
    0.52
     يتيمه
    0.52
     temperament
    0.52
    reportWebVitals
    0.51
    당
    0.51
    Activations Density 5.414%

    No Known Activations