© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12065
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate conditions being met or problems occurring in scientific research

    oai_token-act-pair · gemini-2.0-flash

    fulfill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     fusible
    -0.71
     Workmen
    -0.68
     dumne
    -0.63
     anastom
    -0.60
     fusing
    -0.60
    omitempty
    -0.59
     fused
    -0.59
     merger
    -0.59
     flocc
    -0.58
    \}=
    -0.57
    POSITIVE LOGITS
    <bos>
    1.23
    orice
    0.56
     Total
    0.49
    ----</
    0.49
    ніципалі
    0.49
    ंदीखरीदारी
    0.48
    rete
    0.47
    Total
    0.47
    GOTREF
    0.46
    Lähteet
    0.46
    Activations Density 4.012%

    No Known Activations