© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6208
    Prev
    Next
    INDEX
    Explanations

    citations and acronyms related to scientific publications

    oai_token-act-pair · 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
     néz
    -0.91
     löytyy
    -0.84
     împre
    -0.82
     löyty
    -0.79
     vastaan
    -0.76
     bēr
    -0.75
     aikaa
    -0.75
     tarko
    -0.73
     acoper
    -0.73
     näky
    -0.72
    POSITIVE LOGITS
     af
    0.62
     bezeichneter
    0.62
     ik
    0.61
     ard
    0.61
     ny
    0.60
     az
    0.59
     tir
    0.59
     ing
    0.58
     io
    0.58
     erv
    0.58
    Activations Density 51.331%

    No Known Activations