© 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. 1397
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms, especially player names and statistics

    oai_token-act-pair · gemini-2.0-flash

    Sports stories

    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
     виправивши
    -0.64
     '\\;'
    -0.64
    +#+#
    -0.57
     Sal
    -0.54
    AsUp
    -0.53
    saraba
    -0.50
     Vrij
    -0.50
    ardless
    -0.49
     geslacht
    -0.48
    rawDesc
    -0.47
    POSITIVE LOGITS
     bore
    0.57
    DrawerToggle
    0.54
     nakalista
    0.54
     advanced
    0.52
     f
    0.52
    encodeWith
    0.50
    SizeF
    0.50
    featureID
    0.49
     fle
    0.49
     Feel
    0.49
    Activations Density 6.234%

    No Known Activations