© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11324
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various forms.

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "be"

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

    forms of "to be"

    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
     promoting
    -0.76
     assessing
    -0.75
     evaluating
    -0.74
     examining
    -0.73
     treating
    -0.73
     criticizing
    -0.73
     recommending
    -0.72
     reviewing
    -0.71
     specifying
    -0.69
     inspecting
    -0.69
    POSITIVE LOGITS
     being
    2.44
    being
    2.20
    Being
    2.03
     Being
    1.99
     BEING
    1.96
     étant
    1.49
     bein
    1.42
     sendo
    1.29
     fiind
    1.27
     essere
    1.20
    Activations Density 5.272%

    No Known Activations