© 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. 8658
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C-like syntax and file paths

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash

    say "uppercase"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    MigrationBuilder
    -1.25
    SourceChecksum
    -1.16
     للاسماء
    -1.11
     مشين
    -1.09
    WebVitals
    -1.09
    ஧
    -1.09
    ஡
    -1.09
    <unused38>
    -1.08
    <unused33>
    -1.08
    <unused7>
    -1.08
    POSITIVE LOGITS
    <bos>
    -0.33
     creer
    -0.33
    bibinfo
    -0.33
     skick
    -0.34
    bibfield
    -0.34
    滿
    -0.35
     vän
    -0.35
    同步
    -0.36
     iconFacebook
    -0.36
     verdi
    -0.36
    Activations Density 14.384%

    No Known Activations