© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6506
    Prev
    Next
    INDEX
    Explanations

    the word "customer" along with words that appear near it

    oai_token-act-pair · gemini-2.0-flash

    customer

    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
     africains
    -0.85
     russes
    -0.81
     pitié
    -0.74
     américains
    -0.73
     extérieurs
    -0.72
     honte
    -0.71
     fallu
    -0.71
    يكب
    -0.71
     paroisse
    -0.71
     sociaux
    -0.70
    POSITIVE LOGITS
    uerre
    0.69
     pá
    0.63
     SER
    0.60
    [...,
    0.60
    })));
    0.60
     Bhattach
    0.60
    intur
    0.59
    NOST
    0.59
    endregion
    0.58
     CURIAM
    0.58
    Activations Density 1.783%

    No Known Activations