© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1033
    Prev
    Next
    INDEX
    Explanations

    words and phrases found within formal documents/patents/academic papers.

    oai_token-act-pair · gemini-2.0-flash

    patent/scientific 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     there
    -2.53
    there
    -2.02
     There
    -1.91
    There
    -1.89
     THERE
    -1.86
    THERE
    -1.63
     therefrom
    -1.39
     acolo
    -1.29
     thither
    -1.28
     thereof
    -1.27
    POSITIVE LOGITS
    Jäh
    0.51
    orda
    0.45
    çek
    0.44
    ränkt
    0.41
    باره
    0.41
    ühnen
    0.40
    close
    0.38
    ro
    0.38
    órc
    0.38
     close
    0.37
    Activations Density 1.192%

    No Known Activations