© 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. 7779
    Prev
    Next
    INDEX
    Explanations

    code snippets and tags from XML-based languages like XAML

    oai_token-act-pair · gemini-2.0-flash

    say "template" words

    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
     template
    -2.22
     Template
    -2.19
     templates
    -2.14
     Templates
    -2.08
    Template
    -2.05
    template
    -2.00
     TEMPLATE
    -1.97
    Templates
    -1.95
     模板
    -1.88
    模板
    -1.86
    POSITIVE LOGITS
    postsleuth
    0.58
    StoryboardSegue
    0.47
     ویکی‌پدیا
    0.46
    twimg
    0.46
    ніципа
    0.46
     CanadaChoose
    0.43
     kasarigan
    0.43
    richTextPanel
    0.43
    DMETHOD
    0.42
     BoxFit
    0.42
    Activations Density 1.471%

    No Known Activations