© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6691
    Prev
    Next
    INDEX
    Explanations

    the word "perform"

    oai_token-act-pair · gemini-2.0-flash

    perform

    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
    ();)
    -0.79
     recognise
    -0.75
    %");
    -0.74
    themselves
    -0.73
    neighbour
    -0.72
    ()};
    -0.72
    /−
    -0.69
    behaviour
    -0.69
     neighbourhoods
    -0.69
    !»
    -0.68
    POSITIVE LOGITS
     TextFormField
    0.63
    SupportActionBar
    0.59
     Islas
    0.56
    IntentFilter
    0.55
     couverts
    0.54
    ="@+
    0.54
    halen
    0.53
     Schmer
    0.53
     RestTemplate
    0.53
    enity
    0.52
    Activations Density 2.569%

    No Known Activations