© 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. 284
    Prev
    Next
    INDEX
    Explanations

    the articles "a" and "the"

    oai_token-act-pair · gemini-2.0-flash

    childhood, youth

    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
    ليز
    -0.57
    sizeCache
    -0.53
     Kids
    -0.53
     GenerationType
    -0.52
     ویکی‌پدیا
    -0.52
    kids
    -0.51
    Kids
    -0.50
     defStyleAttr
    -0.50
    nloa
    -0.49
     man
    -0.49
    POSITIVE LOGITS
     médic
    0.61
     resourceCulture
    0.59
    setVerticalGroup
    0.56
    AndEndTag
    0.53
    bogen
    0.52
    ägen
    0.51
    зулта
    0.51
    ()]);
    0.51
    EndGlobalSection
    0.50
    envolvimento
    0.50
    Activations Density 3.017%

    No Known Activations