© 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. 9720
    Prev
    Next
    INDEX
    Explanations

    something about medical scans and methods for dealing with them

    oai_token-act-pair · gemini-2.0-flash

    Scans and data acquisition

    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
     Sk
    -2.03
     SC
    -2.00
     Sc
    -1.98
    Sk
    -1.93
     sk
    -1.91
     scan
    -1.90
     SK
    -1.89
     Scan
    -1.89
     sc
    -1.86
    Sc
    -1.84
    POSITIVE LOGITS
     ویکی‌پدی
    0.58
    verifyException
    0.56
    EndInit
    0.54
    はじめに
    0.54
     مرئيه
    0.52
     Lorenz
    0.51
     keper
    0.50
     Hubert
    0.50
     AssemblyProduct
    0.47
     Mullen
    0.47
    Activations Density 1.727%

    No Known Activations