© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3129
    Prev
    Next
    INDEX
    Explanations

    words used to express surprise or exasperation

    oai_token-act-pair · gemini-2.0-flash

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     >=",
    -0.53
     invokingState
    -0.53
    __":
    -0.49
    μών
    -0.47
    SuspendLayout
    -0.44
    bukti
    -0.44
    ésus
    -0.44
     amid
    -0.44
    原始内容存档于
    -0.43
    ágok
    -0.43
    POSITIVE LOGITS
     utafitiHapana
    0.60
     defaultstate
    0.60
     maxn
    0.59
    хьтан
    0.57
     lenker
    0.57
     nahilalakip
    0.57
     Exactos
    0.55
     esternos
    0.55
    apeake
    0.54
    andte
    0.54
    Activations Density 3.001%

    No Known Activations