© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15362
    Prev
    Next
    INDEX
    Explanations

    a variety of words loosely related to different categories such as sports, health and statistics.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    
    -0.59
    OOTDTY
    -0.52
    
    -0.51
     hiszen
    -0.48
     TextInputType
    -0.44
     fractal
    -0.44
    specifically
    -0.44
     sampler
    -0.43
     ceinture
    -0.43
    Personensuche
    -0.43
    POSITIVE LOGITS
    PMailer
    0.61
     newBuilder
    0.57
     FishBase
    0.54
    bige
    0.54
    DoubleQuotes
    0.53
    appé
    0.53
    ValueGeneration
    0.53
     Roskov
    0.52
     setuptools
    0.51
    жте
    0.50
    Activations Density 6.319%

    No Known Activations