© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3941
    Prev
    Next
    INDEX
    Explanations

    clauses beginning with pronouns or nouns referring to people acting in a narrative

    oai_token-act-pair · gemini-2.0-flash

    baby related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Jurí
    -0.69
    AFX
    -0.54
     חיצוניים
    -0.54
    Abit
    -0.52
     consultato
    -0.51
     تضيفلها
    -0.50
    はじめに
    -0.49
     lubricating
    -0.47
     lubrication
    -0.47
     legale
    -0.46
    POSITIVE LOGITS
     carry
    0.82
     crib
    0.81
     carried
    0.81
     cra
    0.80
    carry
    0.77
     carrier
    0.77
     rocked
    0.76
     carries
    0.74
     rocking
    0.73
     cot
    0.73
    Activations Density 1.211%

    No Known Activations