© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2532
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to academic research, funding, and publications, including abbreviations and foreign words.

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    __":
    -0.58
     ExecuteAsync
    -0.56
    __':
    -0.55
     mergeFrom
    -0.50
    StoryboardSegue
    -0.45
    styleType
    -0.44
     gesso
    -0.44
    piram
    -0.44
    endregion
    -0.44
     "'",
    -0.43
    POSITIVE LOGITS
     gedaan
    0.66
     genoemd
    0.65
     gebou
    0.62
     jäsen
    0.61
    tijden
    0.61
    ніципалі
    0.60
     gehouden
    0.60
     kleuren
    0.59
     gebouw
    0.59
     rijden
    0.58
    Activations Density 20.012%

    No Known Activations