© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14412
    Prev
    Next
    INDEX
    Explanations

    the beginning of words starting with "Ren" or "Ken", and also "Sen"

    oai_token-act-pair · gemini-2.0-flash

    Mentioning "Ken" and "Ren"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    n
    -0.71
    +#+#
    -0.65
    tial
    -0.64
    nant
    -0.63
    ned
    -0.63
    ti
    -0.62
    teil
    -0.62
    ce
    -0.61
    nnnn
    -0.60
     BoxFit
    -0.59
    POSITIVE LOGITS
     насељу
    0.60
    Personensuche
    0.52
     énergé
    0.51
     otomatig
    0.50
     financières
    0.49
     douceur
    0.47
     mères
    0.46
     commerciales
    0.46
    rovnik
    0.45
    ga
    0.45
    Activations Density 2.213%

    No Known Activations