© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    words indicating something was created, completed, or ranked

    oai_token-act-pair · gemini-2.0-flash

    Reviews/Descriptions

    np_max-act · gemini-2.0-flash

    ▁Made

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
     Raised
    -1.10
    Trained
    -1.05
     Told
    -1.04
    Told
    -1.03
    Raised
    -1.02
     Gave
    -0.99
     Spent
    -0.99
     Born
    -0.98
     Took
    -0.97
    Took
    -0.97
    POSITIVE LOGITS
     made
    1.02
     passed
    0.88
     brought
    0.86
     provided
    0.84
     found
    0.83
     created
    0.82
     produced
    0.82
     reached
    0.81
     placed
    0.80
     held
    0.79
    Activations Density 2.726%

    No Known Activations