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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2095
    Prev
    Next
    INDEX
    Explanations

    seemingly random and uninterpretable tokens and short phrases

    oai_token-act-pair · gemini-2.0-flash

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.94
     للاسماء
    -0.64
     Paglinawan
    -0.61
     AdapterView
    -0.60
    Przypisy
    -0.57
    ContentLoaded
    -0.54
    NamedQuery
    -0.54
    مراجع
    -0.52
    __":
    -0.52
    ValueStyle
    -0.51
    POSITIVE LOGITS
    bbene
    0.63
     Forse
    0.57
     latest
    0.52
    etate
    0.51
    שְׁ
    0.51
     Numa
    0.51
     ſch
    0.50
    latest
    0.50
     tind
    0.50
     سكانية
    0.48
    Activations Density 15.378%

    No Known Activations