© 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. 158
    Prev
    Next
    INDEX
    Explanations

    Arabic script and other non-alphanumeric characters, and some words indicating locations and dates.

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    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
     Efq
    -0.79
     whoſe
    -0.68
     فريبيس
    -0.68
     Савезне
    -0.67
     Majefty
    -0.66
     Chriftian
    -0.63
     Jefus
    -0.62
     Monfieur
    -0.60
     houſe
    -0.60
     whofe
    -0.59
    POSITIVE LOGITS
    gameserver
    0.56
     peruan
    0.56
    Rüyada
    0.54
     violenza
    0.52
    ("")]
    0.50
    SuppressWarnings
    0.50
    )]=
    0.50
     Justiça
    0.50
     Reglamento
    0.50
    CppCodeGen
    0.49
    Activations Density 1.284%

    No Known Activations