© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12675
    Prev
    Next
    INDEX
    Explanations

    acronyms, abbreviations for research institutions and government organizations.

    oai_token-act-pair · gemini-2.0-flash

    organizations

    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
     haystack
    -0.53
     whispers
    -0.52
     chuckle
    -0.51
    izzling
    -0.51
     whisper
    -0.51
     bucket
    -0.51
     giggle
    -0.50
    GOTREF
    -0.50
     buckets
    -0.50
    NullCheck
    -0.49
    POSITIVE LOGITS
    '},
    0.57
    <bos>
    0.52
     Вікіпе
    0.50
    roek
    0.49
    limus
    0.48
    ніципалі
    0.47
    AdapterFactory
    0.47
    batore
    0.46
    .")
    0.45
     ISTAT
    0.44
    Activations Density 38.128%

    No Known Activations