© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8608
    Prev
    Next
    INDEX
    Explanations

    clauses that are interrupted by other, non-essential clauses

    oai_token-act-pair · gemini-2.0-flash

    Narrative / Story structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    XmlAccessType
    -0.85
    Geplaatst
    -0.77
    CrossRef
    -0.76
     Biôgrafia
    -0.70
    ChildScrollView
    -0.70
    KommentareTeilen
    -0.66
     Drapeau
    -0.65
    ANSA
    -0.65
    principalTable
    -0.65
    :✨
    -0.63
    POSITIVE LOGITS
    éraires
    0.41
    getRuntime
    0.39
     riêng
    0.37
    onomia
    0.37
     nhà
    0.37
    herren
    0.36
     lộ
    0.35
    agra
    0.35
     success
    0.35
     получилось
    0.35
    Activations Density 2.733%

    No Known Activations