© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3710
    Prev
    Next
    INDEX
    Explanations

    negations with "n't"

    oai_token-act-pair · gemini-2.0-flash

    wasn't/wouldn't

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -1.53
     Monfieur
    -1.49
     Efq
    -1.44
     Jefus
    -1.43
     ſche
    -1.41
     houſe
    -1.41
     fevere
    -1.40
     Theſe
    -1.37
     Houſe
    -1.36
     ſever
    -1.35
    POSITIVE LOGITS
     do
    0.71
     
    0.69
     (
    0.68
     D
    0.66
     K
    0.66
     L
    0.65
    ↵
    0.63
      
    0.63
     B
    0.62
     [
    0.62
    Activations Density 1.920%

    No Known Activations