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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12684
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and symbols often found in academic citations and scientific writing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     special
    -0.49
    vo
    -0.49
    arnos
    -0.46
    ній
    -0.45
    ago
    -0.45
     vic
    -0.45
    nov
    -0.45
    Abit
    -0.45
    ut
    -0.44
     Nach
    -0.44
    POSITIVE LOGITS
     JpaRepository
    0.78
    openConnection
    0.68
    ContentAsync
    0.68
    HomeAsUpEnabled
    0.68
    abestanden
    0.66
    déric
    0.65
    WriteTagHelper
    0.65
    GraphicsUnit
    0.64
    Demografia
    0.63
     فريبيس
    0.61
    Activations Density 31.346%

    No Known Activations