© 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. 14776
    Prev
    Next
    INDEX
    Explanations

    the word "this" followed by a noun or verb

    oai_token-act-pair · gemini-2.0-flash

    This

    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
    InjectAttribute
    -0.74
     AssemblyTitle
    -0.74
     <<<<<<<<<<<<<<
    -0.73
     مشين
    -0.73
    expandindo
    -0.69
    RenderAtEndOf
    -0.68
     have
    -0.68
    ReusableCell
    -0.67
    存于互联网档案馆
    -0.66
    Tikang
    -0.66
    POSITIVE LOGITS
     elettrica
    0.57
     devriez
    0.57
     giapp
    0.57
     scolas
    0.55
     politiet
    0.54
     vantaggi
    0.52
     préférence
    0.52
     izquier
    0.51
     Sets
    0.51
    ườ
    0.51
    Activations Density 3.216%

    No Known Activations