© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13712
    Prev
    Next
    INDEX
    Explanations

    the word "criteria", and also has minor association with evaluation

    oai_token-act-pair · gemini-2.0-flash

    criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     criteria
    -1.95
     Criteria
    -1.71
    Criteria
    -1.64
    criteria
    -1.61
     criterion
    -1.42
     CRITERIA
    -1.33
     criter
    -1.12
     Kriterien
    -1.12
     critères
    -1.01
     критери
    -0.96
    POSITIVE LOGITS
     betweenstory
    0.96
     propOrder
    0.81
     réguli
    0.80
     AssemblyProduct
    0.77
    AccessorTable
    0.77
    TagMode
    0.76
    URLException
    0.74
    ISupport
    0.73
     financières
    0.73
     étrangères
    0.71
    Activations Density 2.601%

    No Known Activations