© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8850
    Prev
    Next
    INDEX
    Explanations

    words related to actions, persons, and adjectives typically ending with a "s" sound.

    oai_token-act-pair · gemini-2.0-flash

    ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ous
    -0.91
    ously
    -0.73
    ousness
    -0.68
    OUS
    -0.67
     propOrder
    -0.61
    afficheront
    -0.59
    ナメント
    -0.58
     Ang
    -0.55
    iously
    -0.55
    InstrumentedTest
    -0.53
    POSITIVE LOGITS
    NameInMap
    0.66
     rekening
    0.50
     lode
    0.50
    SBATCH
    0.50
     raiſ
    0.49
    awakeFromNib
    0.47
     HttpHeaders
    0.47
     anſ
    0.46
     uveden
    0.46
     smelled
    0.45
    Activations Density 9.358%

    No Known Activations