© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4464
    Prev
    Next
    INDEX
    Explanations

    the word "bread" and related words like "loaf" and "traditional"

    oai_token-act-pair · gemini-2.0-flash

    bread

    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
     `{
    -0.67
     stället
    -0.58
     domésticos
    -0.58
    Be
    -0.57
     skall
    -0.56
     possam
    -0.55
    tır
    -0.53
    Cant
    -0.52
    вест
    -0.52
     possa
    -0.51
    POSITIVE LOGITS
    veyard
    0.69
    曖昧さ回避
    0.69
    Siapa
    0.66
    kháu
    0.66
    TypedDataSet
    0.66
    ANTAGES
    0.65
    Lieferumfang
    0.64
    LookAnd
    0.64
    มาะ
    0.64
    NamedQueries
    0.63
    Activations Density 0.829%

    No Known Activations