© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13179
    Prev
    Next
    INDEX
    Explanations

    capital letters, especially J, B, Q, D, N, T, Z and P

    oai_token-act-pair · gemini-2.0-flash

    Code or Initials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     estekak
    -0.76
    сылкі
    -0.71
     ComVisible
    -0.70
    AsUp
    -0.67
    UrlResolution
    -0.66
     ویکی‌پدیا
    -0.66
    رشف
    -0.64
    KommentareTeilen
    -0.63
     nakalista
    -0.63
    Tracce
    -0.58
    POSITIVE LOGITS
    ValueStyle
    0.56
     SDLK
    0.47
    oredCriteria
    0.46
    omeness
    0.45
     Loth
    0.43
    LEncoder
    0.42
    ccl
    0.42
     ilu
    0.41
     aha
    0.41
    &.
    0.41
    Activations Density 0.460%

    No Known Activations