© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12235
    Prev
    Next
    INDEX
    Explanations

    text from a news article, possibly about an election, and more likely to be the intro

    oai_token-act-pair · gemini-2.0-flash

    Formal written texts

    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
    Géographie
    -0.78
     ویکی‌پدیا
    -0.77
     الرياضيه
    -0.75
    BeginContext
    -0.65
     kiệm
    -0.64
    цездатний
    -0.63
    GEBURTSDATUM
    -0.61
    Билгалдахарш
    -0.61
    itesse
    -0.59
    FieldDescriptor
    -0.59
    POSITIVE LOGITS
     Vanguard
    0.51
     THIS
    0.47
    mon
    0.46
     precisely
    0.43
    THIS
    0.42
    ատ
    0.42
    ato
    0.41
    ртуаль
    0.41
     nakalista
    0.41
     parle
    0.40
    Activations Density 1.537%

    No Known Activations