© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12815
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and adverbs like "even" and "much"

    oai_token-act-pair · gemini-2.0-flash

    Adjectives of magnitude

    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
     funniest
    -0.66
    koper
    -0.64
     funnier
    -0.63
     smoother
    -0.63
     ujednoznacz
    -0.61
     fresher
    -0.59
     ExecuteAsync
    -0.59
     wilder
    -0.59
     happier
    -0.59
     sweeter
    -0.57
    POSITIVE LOGITS
     fast
    0.95
     easy
    0.86
     strong
    0.83
    easy
    0.75
     low
    0.75
     high
    0.74
     deep
    0.74
     large
    0.74
     big
    0.73
     quick
    0.69
    Activations Density 0.998%

    No Known Activations