© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1772
    Prev
    Next
    INDEX
    Explanations

    questions, especially starting with "can", "could", "why", or "please"

    oai_token-act-pair · gemini-2.0-flash

    questions starting with "Can"

    np_token-act-pair-logits · gpt-4o-mini

    can/could

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     itſelf
    -0.67
    windowFixed
    -0.63
     ་་
    -0.61
    ſelves
    -0.59
     Stande
    -0.58
    antaine
    -0.57
     ſind
    -0.56
     Heber
    -0.56
    numerusform
    -0.56
     ―――――
    -0.56
    POSITIVE LOGITS
     they
    1.20
     you
    1.10
     this
    1.05
     it
    1.04
     we
    0.95
     these
    0.93
     the
    0.83
     that
    0.82
     he
    0.79
     there
    0.74
    Activations Density 2.651%

    No Known Activations