© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9301
    Prev
    Next
    INDEX
    Explanations

    the letter x

    oai_token-act-pair · gemini-2.0-flash

    x

    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
    Negative Logits
    x
    -1.09
     كومونز
    -0.98
    Czytaj
    -0.79
    xing
    -0.71
    xed
    -0.70
    — 
    -0.70
    xes
    -0.70
    ICAGO
    -0.66
    sätzlich
    -0.66
     بيها
    -0.66
    POSITIVE LOGITS
     X
    1.02
     x
    0.61
     XY
    0.59
    urlopen
    0.59
     xy
    0.58
     XI
    0.56
     Xs
    0.56
     XX
    0.53
     XYZ
    0.53
     Zem
    0.52
    Activations Density 1.530%

    No Known Activations