© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5440
    Prev
    Next
    INDEX
    Explanations

    present tense verbs, especially forms of "to be" and words indicating current activity or academic study.

    oai_token-act-pair · gemini-2.0-flash

    current actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     work
    -0.57
    Work
    -0.54
    copg
    -0.54
    }}],
    -0.53
     WORK
    -0.53
    abestanden
    -0.52
    work
    -0.52
     Work
    -0.51
    "]="
    -0.50
    autoIncrement
    -0.50
    POSITIVE LOGITS
    aarrggbb
    0.63
    ConstraintMaker
    0.52
    initComponents
    0.50
     tør
    0.49
     חיצוניים
    0.48
    sią
    0.48
    ValueGenerated
    0.48
    ✨:
    0.47
     AssemblyProduct
    0.46
     <=",
    0.45
    Activations Density 9.473%

    No Known Activations