© 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. 3085
    Prev
    Next
    INDEX
    Explanations

    words related to artistic intent and technical specifications

    oai_token-act-pair · gemini-2.0-flash

    aesthetic

    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
    Negative Logits
     
    -0.72
     The
    -0.68
     (
    -0.62
     axons
    -0.59
    1
    -0.57
    ://
    -0.56
    The
    -0.56
     «
    -0.54
    iniest
    -0.52
    dani
    -0.52
    POSITIVE LOGITS
    
    0.96
     feroit
    0.91
     kasarigan
    0.90
     auroit
    0.89
     étoient
    0.87
     étoit
    0.85
     ainfi
    0.84
    ):}
    0.84
    ".
    0.84
     avoient
    0.83
    Activations Density 1.212%

    No Known Activations