© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5295
    Prev
    Next
    INDEX
    Explanations

    the word "how"

    oai_token-act-pair · gemini-2.0-flash

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     how
    -0.99
    how
    -0.99
     enfans
    -0.90
     kasarigan
    -0.85
     fermés
    -0.77
     hvordan
    -0.74
     oreille
    -0.73
     oreilles
    -0.72
     kereszt
    -0.72
     چگونه
    -0.71
    POSITIVE LOGITS
    ophys
    0.61
    sez
    0.57
    malade
    0.57
     Furthermore
    0.57
     Moreover
    0.57
    новниш
    0.56
    ckeys
    0.55
    nibal
    0.54
    zość
    0.54
    osocial
    0.53
    Activations Density 0.396%

    No Known Activations