© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6665
    Prev
    Next
    INDEX
    Explanations

    words related to scientific or mathematical calculations, parameters, and limits

    oai_token-act-pair · gemini-2.0-flash

    finite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -1.38
     itſelf
    -1.25
     Jefus
    -1.23
     Reſ
    -1.16
     Eſ
    -1.14
    ſelves
    -1.13
     Houſe
    -1.11
     Chriſt
    -1.11
     Diſ
    -1.09
     Majefty
    -1.08
    POSITIVE LOGITS
     qu
    0.62
     p
    0.59
    voort
    0.59
     z
    0.59
    psies
    0.58
     po
    0.58
     w
    0.58
    celle
    0.57
     ab
    0.57
     c
    0.57
    Activations Density 1.553%

    No Known Activations