© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3890
    Prev
    Next
    INDEX
    Explanations

    the word "even", often followed by "though" or "in"

    oai_token-act-pair · gemini-2.0-flash

    even

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     समीक्षाओं
    -0.58
    JvmStatic
    -0.56
    also
    -0.54
     also
    -0.54
    WriteTagHelper
    -0.54
     GoogleFonts
    -0.52
    BeginContext
    -0.52
     دیکھیے
    -0.52
    VolleyError
    -0.51
    leqq
    -0.50
    POSITIVE LOGITS
     виправивши
    0.58
    RenderAtEndOf
    0.56
     prêtres
    0.52
    ostomy
    0.52
    complexContent
    0.51
    kannya
    0.49
    arnia
    0.49
     godt
    0.48
     sementara
    0.48
    гази
    0.48
    Activations Density 1.245%

    No Known Activations