© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3872
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    oai_token-act-pair · gemini-2.0-flash

    German and "-er" suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    itron
    -0.53
    arge
    -0.52
    ULATOR
    -0.52
    ädie
    -0.51
    sieu
    -0.50
    äumt
    -0.48
    comy
    -0.48
     AppCompatTheme
    -0.48
    zości
    -0.47
    setCount
    -0.47
    POSITIVE LOGITS
     bigger
    1.05
     stronger
    1.00
     than
    1.00
    bigger
    0.99
     tighter
    0.95
     sharper
    0.95
     deeper
    0.94
     longer
    0.93
     quicker
    0.93
     larger
    0.91
    Activations Density 0.588%

    No Known Activations