© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10662
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to saying goodbye to something, either literally or figuratively

    oai_token-act-pair · gemini-2.0-flash

    say

    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
     censiti
    -0.63
    StoryboardSegue
    -0.62
     للمعارف
    -0.57
    ruptedException
    -0.51
    shadowOffset
    -0.49
    TypedDataSet
    -0.49
    RegistryLite
    -0.49
    HttpPost
    -0.47
    WithMany
    -0.47
    Sucesor
    -0.45
    POSITIVE LOGITS
     say
    2.58
     saying
    2.48
    say
    2.33
    Say
    2.27
     Say
    2.27
     SAY
    2.16
    saying
    2.11
     Saying
    2.08
    Saying
    2.05
     said
    2.02
    Activations Density 1.260%

    No Known Activations