© 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. 14390
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and adverbs used in restaurant or travel reviews

    oai_token-act-pair · gemini-2.0-flash

    Intensifiers

    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
    Negative Logits
     architet
    -0.46
    ArrowToggle
    -0.44
     Öffentlichkeit
    -0.44
     raccont
    -0.43
     guerre
    -0.39
     ворота
    -0.39
     púb
    -0.39
     iglesia
    -0.39
     отношения
    -0.38
     igreja
    -0.38
    POSITIVE LOGITS
     }}"></
    0.98
    StoryboardSegue
    0.98
    rungsseite
    0.96
     '\\;'
    0.88
    RenderAtEndOf
    0.88
    GEBURTSDATUM
    0.85
    Personensuche
    0.80
    EndGlobalSection
    0.75
    onActivityResult
    0.73
     typelib
    0.73
    Activations Density 1.275%

    No Known Activations