© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11728
    Prev
    Next
    INDEX
    Explanations

    code-related terms and identifiers, especially within the context of Azure cloud services

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     IRIS
    -0.62
     PRD
    -0.60
     Agamemnon
    -0.54
     Hyperion
    -0.54
     LDA
    -0.53
     espagne
    -0.52
     Ecclesiastical
    -0.52
     EEU
    -0.52
     Odysseus
    -0.51
     medusa
    -0.50
    POSITIVE LOGITS
     for
    0.81
     that
    0.80
     is
    0.78
     from
    0.78
     the
    0.78
     of
    0.77
     to
    0.77
     this
    0.76
     who
    0.76
     by
    0.75
    Activations Density 16.711%

    No Known Activations