© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15874
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be" (is, are, was, been).

    oai_token-act-pair · gemini-2.0-flash

    is/are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    RenderAtEndOf
    -0.93
    IContainer
    -0.82
    UnusedPrivate
    -0.78
     мәкал
    -0.75
    IsContent
    -0.75
    complexContent
    -0.73
     Roskov
    -0.72
    IActionResult
    -0.69
    Portály
    -0.69
    UnknownFields
    -0.69
    POSITIVE LOGITS
     متعلقه
    0.56
     تانيه
    0.52
     able
    0.51
     suitable
    0.49
     considered
    0.49
     focused
    0.48
     cited
    0.46
     dependent
    0.45
     ready
    0.45
     compatible
    0.44
    Activations Density 4.982%

    No Known Activations