© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7866
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "How" or "What"

    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_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
    Negative Logits
     how
    -1.69
    how
    -1.55
    How
    -1.46
     How
    -1.41
    <bos>
    -1.38
    HOW
    -1.30
     HOW
    -1.28
     hvordan
    -1.06
     cómo
    -1.05
    cómo
    -1.02
    POSITIVE LOGITS
    ResponseStatus
    0.50
    orry
    0.49
    nolia
    0.49
    jublj
    0.47
     Newswire
    0.47
    erals
    0.46
     Invis
    0.46
    ynchronous
    0.46
     forsake
    0.46
     robin
    0.45
    Activations Density 0.568%

    No Known Activations