Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7259
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" in its various forms

    oai_token-act-pair · gemini-2.0-flash

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     is
    -0.76
    Билгалдахарш
    -0.74
     Is
    -0.65
     romantique
    -0.60
     culturelles
    -0.59
     relève
    -0.59
     roulant
    -0.59
     isn
    -0.58
    ❋
    -0.58
    belief
    -0.57
    POSITIVE LOGITS
    adaptiveStyles
    0.72
    Previously
    0.57
     Previously
    0.56
    RenderAtEndOf
    0.56
     Había
    0.56
    makeText
    0.54
    (',',
    0.53
    FailureListener
    0.52
     Audiodateien
    0.52
    ">//
    0.51
    Activations Density 0.827%

    No Known Activations