© 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. 6679
    Prev
    Next
    INDEX
    Explanations

    LaTeX code expressions

    oai_token-act-pair · 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
     +
    -2.22
    +
    -1.79
     "+
    -1.79
     '+
    -1.78
     $+
    -1.68
     $+$
    -1.65
    '+
    -1.59
    "+
    -1.57
     +
    -1.52
    ="+
    -1.48
    POSITIVE LOGITS
     brancas
    0.50
     rhestr
    0.45
    HasForeignKey
    0.44
    ⃣
    0.43
    üedad
    0.43
    経歴
    0.42
    ėjas
    0.42
    ฒ
    0.41
    ழ
    0.41
     vermelhas
    0.41
    Activations Density 1.857%

    No Known Activations