© 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. 15632
    Prev
    Next
    INDEX
    Explanations

    a mix of Indonesian, German (and possibly other) words in addition to English words, especially conversational phrases, possibly from a blog.

    oai_token-act-pair · gemini-2.0-flash

    Internet/code snippets

    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
     ninguém
    -0.72
    +#+#
    -0.71
     Pyrr
    -0.63
    بوابة
    -0.62
     חיצוניים
    -0.60
     avoient
    -0.59
     يتيمه
    -0.59
     Nadie
    -0.59
     Charlemagne
    -0.59
     Hoje
    -0.59
    POSITIVE LOGITS
     do
    0.49
     self
    0.48
     *>(
    0.48
     he
    0.47
    XmlAccessType
    0.46
     CYTHON
    0.46
    ibol
    0.45
     Mr
    0.45
    -
    0.44
     son
    0.44
    Activations Density 0.945%

    No Known Activations