© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    various forms of numerical identifiers and symbols

    oai_token-act-pair · gemini-2.0-flash

    say "number 8"

    np_max-act-logits · gemini-2.0-flash

    say "8"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    enderror
    -0.67
     doInBackground
    -0.56
     nineteen
    -0.56
     Италијани
    -0.55
     viewDidLoad
    -0.54
    BagLayout
    -0.52
    LayoutStyle
    -0.51
     للمعارف
    -0.51
    AccessorTable
    -0.49
     seventeenth
    -0.48
    POSITIVE LOGITS
    8
    1.44
     eight
    1.09
     Eight
    0.99
     Eighth
    0.98
     eighth
    0.93
    八
    0.90
     delapan
    0.87
     huit
    0.87
     acht
    0.85
     EIGHT
    0.85
    Activations Density 5.115%

    No Known Activations