© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9760
    Prev
    Next
    INDEX
    Explanations

    code, math and logical operators, and the word 'that'

    oai_token-act-pair · gemini-2.0-flash

    technical writing/slashes/cliches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     RSSSF
    -0.54
    벳
    -0.54
    ntö
    -0.52
    íncia
    -0.50
    sodik
    -0.50
     thus
    -0.50
     therefore
    -0.49
    ิลปะ
    -0.48
    之一
    -0.47
     annehmen
    -0.47
    POSITIVE LOGITS
    TypedDataSet
    1.03
    تقاوى
    0.96
     ModelExpression
    0.91
    tvguidetime
    0.88
    WebVitals
    0.86
    ISupport
    0.84
     protoimpl
    0.84
     resourceCulture
    0.84
    BeginContext
    0.83
    GEBURTSDATUM
    0.82
    Activations Density 5.309%

    No Known Activations