© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    the word "capable"

    oai_token-act-pair · gemini-2.0-flash

    capable

    np_max-act · gemini-2.0-flash

    ▁capable

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ^(@)
    -0.82
    ंदीखरीदारी
    -0.81
     virginity
    -0.81
     GenerationType
    -0.79
    PreferredItem
    -0.78
    WebVitals
    -0.75
    RectangleBorder
    -0.75
     Cowper
    -0.74
     moschino
    -0.74
     nemico
    -0.72
    POSITIVE LOGITS
     former
    0.72
    </em>
    0.62
     current
    0.61
     the
    0.60
    ם
    0.59
    ing
    0.57
     
    0.56
     procu
    0.56
     new
    0.56
    <em>
    0.56
    Activations Density 0.317%

    No Known Activations