© 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
    2. Gemma-2-2B
    3. 18-GEMMASCOPE-TRANSCODER-16K
    4. 7929
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to learning from mistakes in high-risk situations, especially nuclear disasters, with a focus on the Fukushima incident.

    oai_token-act-pair · gemini-2.0-flash

    World events, nuclear energy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Theſe
    -0.66
    Бахар
    -0.66
     GenerationType
    -0.65
     myſelf
    -0.64
    AppMethodBeat
    -0.61
    κέ
    -0.60
     iſt
    -0.59
     оригіналу
    -0.57
     testé
    -0.57
     himſelf
    -0.57
    POSITIVE LOGITS
    NamedQueries
    0.64
    TypedDataSet
    0.53
     Mahesh
    0.50
    Zunanje
    0.49
    кипе
    0.47
     Paralymp
    0.45
    Sucesor
    0.44
    Tē
    0.44
    pieza
    0.44
     комби
    0.44
    Activations Density 1.055%

    No Known Activations