© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11109
    Prev
    Next
    INDEX
    Explanations

    short word fragments

    oai_token-act-pair · gemini-2.0-flash

    Text fragments / code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     sest
    -0.65
    .
    -0.56
     (
    -0.55
     ex
    -0.54
    感
    -0.53
     éx
    -0.52
     Ex
    -0.52
    my
    -0.52
    "
    -0.52
     "
    -0.52
    POSITIVE LOGITS
    msgSender
    1.13
     propOrder
    1.10
    FTFY
    1.08
    addCriterion
    1.06
    Gambas
    0.97
     avoient
    0.96
     ویکی‌پدیای
    0.95
     quelcon
    0.95
     feroit
    0.94
    @[+][
    0.93
    Activations Density 2.721%

    No Known Activations