© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people and their actions

    oai_token-act-pair · gemini-2.0-flash

    brothers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     تضيفلها
    -0.64
     collectively
    -0.53
     ujednoznacz
    -0.52
    zonych
    -0.50
     nocturna
    -0.48
    huizen
    -0.47
    ETERS
    -0.47
     poches
    -0.46
     []*
    -0.46
    Ecotoxicity
    -0.46
    POSITIVE LOGITS
    utilisons
    0.81
     otomatig
    0.63
    LookAnd
    0.63
    Smarty
    0.60
    EndContext
    0.56
    ftagPool
    0.55
    BoxShadow
    0.54
    richTextPanel
    0.53
     الحره
    0.53
    complexType
    0.53
    Activations Density 8.788%

    No Known Activations