© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8976
    Prev
    Next
    INDEX
    Explanations

    the word "was" and forms of "is"

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    toz
    -0.49
    êtement
    -0.48
     Polym
    -0.48
    feels
    -0.48
      (
    -0.47
    rodu
    -0.47
    typeDefinition
    -0.47
    )$_
    -0.46
    pila
    -0.45
     Aden
    -0.44
    POSITIVE LOGITS
    +#+#
    0.71
    WebVitals
    0.61
    WaitGroup
    0.57
     contextLoads
    0.56
     defaultstate
    0.55
     محفوظة
    0.54
    stateProvider
    0.52
     endometrial
    0.49
     AssemblyVersion
    0.48
    HandlerContext
    0.48
    Activations Density 4.481%

    No Known Activations