© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12389
    Prev
    Next
    INDEX
    Explanations

    uses of the word "and" in close proximity to other conjunctions, articles, or prepositions

    oai_token-act-pair · gemini-2.0-flash

    programming or code-related terms

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

    and

    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
     tão
    -0.36
     instead
    -0.33
     and
    -0.33
     invece
    -0.31
    instead
    -0.29
     che
    -0.29
     or
    -0.28
    ും
    -0.28
     andato
    -0.28
    addCriterion
    -0.27
    POSITIVE LOGITS
    NameInMap
    0.95
    RenderAtEndOf
    0.85
     strength
    0.84
     nakalista
    0.82
    IntoConstraints
    0.81
    +:+
    0.80
     bravery
    0.77
     accessibility
    0.77
     flexibility
    0.77
    UserScript
    0.76
    Activations Density 2.957%

    No Known Activations