© 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. 11744
    Prev
    Next
    INDEX
    Explanations

    sentences expressing opinions especially including people and ethics

    oai_token-act-pair · gemini-2.0-flash

    uncommon or complex terms

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

    News and statements

    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
    كتشاف
    -0.63
    kuuta
    -0.60
    ]";
    -0.60
    ]');
    -0.59
     onCreateView
    -0.59
    MessageOf
    -0.58
    ruptedException
    -0.57
     AssemblyTitle
    -0.56
    ']."
    -0.55
    逅
    -0.55
    POSITIVE LOGITS
     MainAxisSize
    0.55
    Xna
    0.51
     fortsetter
    0.50
     elettrico
    0.47
     kasarigan
    0.47
    RegressionTest
    0.47
     primeras
    0.46
     âgées
    0.46
    dep
    0.46
    Pyx
    0.46
    Activations Density 1.274%

    No Known Activations