© 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. 10386
    Prev
    Next
    INDEX
    Explanations

    phrases about living and being

    oai_token-act-pair · gemini-2.0-flash

    live

    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
    MLLoader
    -0.73
    出版年
    -0.64
    routeProvider
    -0.62
    GoogleApiClient
    -0.59
    complexType
    -0.56
    ########.
    -0.56
     beginnetje
    -0.55
    ifrance
    -0.54
    IsInitialized
    -0.54
    ActionEvent
    -0.53
    POSITIVE LOGITS
     JADX
    0.55
     مُعرِّف
    0.55
    messageInfo
    0.53
    interopRequire
    0.52
    ภัณฑ์
    0.50
    isContained
    0.48
    ríklad
    0.47
     GENERATED
    0.47
     ASN
    0.46
    ($__
    0.46
    Activations Density 1.491%

    No Known Activations