© 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. 8993
    Prev
    Next
    INDEX
    Explanations

    the `get; set;` C# property pattern

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    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
    KommentareTeilen
    -0.84
     الحره
    -0.82
     betweenstory
    -0.75
    )."
    -0.74
    archiviato
    -0.74
    ".
    -0.72
    ”.
    -0.71
    存于互联网档案馆
    -0.71
    \{\\
    -0.71
    ".
    -0.70
    POSITIVE LOGITS
     iLocal
    0.54
     run
    0.49
     set
    0.47
    load
    0.47
     vo
    0.45
    set
    0.44
     soak
    0.44
     load
    0.44
     con
    0.42
    jo
    0.42
    Activations Density 1.847%

    No Known Activations