© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10437
    Prev
    Next
    INDEX
    Explanations

    words and phrases of comparison or contrast

    oai_token-act-pair · gemini-2.0-flash

    look

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    aesthetic
    -0.78
    Aesthetic
    -0.71
     aesthetically
    -0.71
     aesthetics
    -0.71
     aesthetic
    -0.66
    \{\\
    -0.65
     Aesthetic
    -0.65
     mergeFrom
    -0.64
     Aesthetics
    -0.60
     AssemblyVersion
    -0.57
    POSITIVE LOGITS
     look
    1.22
    look
    1.11
     Look
    1.02
     looking
    1.02
    Look
    1.00
    looking
    0.94
     LOOK
    0.86
     LOOKING
    0.81
    LOOK
    0.80
     looks
    0.79
    Activations Density 1.884%

    No Known Activations