© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7095
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal, academic and medical documents

    oai_token-act-pair · gemini-2.0-flash

    legal and technical language

    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
     raiſ
    -0.79
     uſed
    -0.77
     Reſ
    -0.77
     myſelf
    -0.75
     againſt
    -0.74
     itſelf
    -0.74
     Anſ
    -0.73
     Conſ
    -0.73
     Monfieur
    -0.72
     fevere
    -0.71
    POSITIVE LOGITS
    a
    0.51
    Personendaten
    0.51
     nahilalakip
    0.50
    f
    0.49
    Hentet
    0.49
    MigrationBuilder
    0.47
    protoimpl
    0.47
    i
    0.47
     الدولى
    0.44
    mybatisplus
    0.42
    Activations Density 19.498%

    No Known Activations