© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3692
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging the user to continue reading

    oai_token-act-pair · gemini-2.0-flash

    Reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     незавершена
    -0.95
     invokingState
    -0.83
     Vikipedi
    -0.71
    InjectAttribute
    -0.70
    الدراسه
    -0.68
     насељу
    -0.66
    IntoConstraints
    -0.65
     '\\;'
    -0.65
    énario
    -0.63
     <>",
    -0.63
    POSITIVE LOGITS
     carre
    0.55
    zen
    0.53
    cie
    0.51
     pó
    0.49
    <eos>
    0.47
     exert
    0.45
    =_
    0.45
    ิ่ม
    0.45
    return
    0.45
    aro
    0.45
    Activations Density 0.610%

    No Known Activations