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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3716
    Prev
    Next
    INDEX
    Explanations

    the words "it," "is," "there," "we," "you," and other similar pronouns and helping verbs

    oai_token-act-pair · gemini-2.0-flash

    common forms of the verb "to be"

    np_token-act-pair-logits · gpt-4o-mini

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     it
    -0.72
     оно
    -0.68
    它
    -0.59
     itſelf
    -0.58
     Оно
    -0.58
    WriteTagHelper
    -0.55
     그것
    -0.54
     它
    -0.54
    It
    -0.54
     SqlCommand
    -0.52
    POSITIVE LOGITS
     is
    1.13
     has
    0.80
     isn
    0.79
     was
    0.77
     AssemblyCulture
    0.73
     occurs
    0.73
     happens
    0.71
     gets
    0.69
     comes
    0.67
     relies
    0.67
    Activations Density 4.653%

    No Known Activations