© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    qualifiers like "but" and "so" and other words that change the meaning or direction of a sentence

    oai_token-act-pair · gemini-2.0-flash

    interrogative words

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

    comma or so

    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
    expandindo
    -0.59
    "}")
    -0.58
    (")
    -0.56
    verwijspagina
    -0.53
    (')
    -0.52
    ukunfts
    -0.52
    wikimedia
    -0.51
    QtGui
    -0.50
     firebaseConfig
    -0.50
    quelize
    -0.50
    POSITIVE LOGITS
     how
    2.31
     why
    1.78
     what
    1.76
    how
    1.70
     bagaimana
    1.45
    what
    1.44
     hvordan
    1.43
    why
    1.42
     cómo
    1.41
     HOW
    1.31
    Activations Density 15.380%

    No Known Activations