© 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. 3938
    Prev
    Next
    INDEX
    Explanations

    words and phrases often used in legal or formal documents and government reports

    oai_token-act-pair · gemini-2.0-flash

    say "the"

    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
     refusé
    -0.48
     trabajado
    -0.44
     tenido
    -0.44
     jueces
    -0.43
     slutet
    -0.42
     privadas
    -0.41
     ontvang
    -0.41
     potuto
    -0.40
    )!
    -0.40
     venido
    -0.40
    POSITIVE LOGITS
     The
    0.98
    rawDesc
    0.85
     purpoſe
    0.79
    WebVitals
    0.75
     pleaſure
    0.73
     These
    0.71
     Our
    0.71
    findpost
    0.70
     reaſon
    0.68
     leaſt
    0.66
    Activations Density 16.961%

    No Known Activations