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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10254
    Prev
    Next
    INDEX
    Explanations

    words indicating addition

    oai_token-act-pair · gemini-2.0-flash

    also

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     also
    -2.67
    also
    -2.22
    Also
    -2.03
     Also
    -1.94
     também
    -1.91
     también
    -1.89
     juga
    -1.75
     også
    -1.70
     также
    -1.66
     także
    -1.58
    POSITIVE LOGITS
    WebVitals
    0.84
    apimachinery
    0.77
    InstrumentedTest
    0.71
    Filmografia
    0.70
    XmlEnum
    0.70
     resourceCulture
    0.69
    ynos
    0.69
    queryInterface
    0.68
    adaptiveStyles
    0.67
    EDEFAULT
    0.67
    Activations Density 1.453%

    No Known Activations