© 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. 12074
    Prev
    Next
    INDEX
    Explanations

    a variety of language patterns, including math symbols, place names, personal statements, gardening terms, and birth-related words.

    oai_token-act-pair · gemini-2.0-flash

    going

    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
    QMetaType
    -0.88
     noDo
    -0.84
     AssemblyTitle
    -0.73
     OFDb
    -0.68
     himo
    -0.68
    principalTable
    -0.63
     autorytatywna
    -0.63
    antMatchers
    -0.63
    ArrowToggle
    -0.62
     betweenstory
    -0.62
    POSITIVE LOGITS
     going
    2.63
     Going
    2.11
     GOING
    2.08
    Going
    2.08
    going
    1.98
    GOING
    1.46
     goin
    1.40
    goin
    0.98
     goi
    0.88
     gonna
    0.77
    Activations Density 13.852%

    No Known Activations