© 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. 6482
    Prev
    Next
    INDEX
    Explanations

    instances of someone making a promise

    oai_token-act-pair · gemini-2.0-flash

    promises

    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
    I
    -0.62
    -
    -0.60
    H
    -0.59
    L
    -0.58
     meu
    -0.58
    D
    -0.57
    S
    -0.56
     promised
    -0.55
    x
    -0.55
    POSITIVE LOGITS
    tvguidetime
    1.04
    ✨:
    0.93
    OGND
    0.91
    verwijspagina
    0.90
     MessageBoxIcon
    0.89
    WebVitals
    0.88
    "}>
    0.88
     BoxFit
    0.88
     שוליים
    0.88
     autorytatywna
    0.86
    Activations Density 1.358%

    No Known Activations