© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1366
    Prev
    Next
    INDEX
    Explanations

    words and phrases of high emotional intensity, both positive and negative

    oai_token-act-pair · gemini-2.0-flash

    political/physical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Chwiliwch
    -0.75
    ValueStyle
    -0.62
     Emotion
    -0.57
     Audiodateien
    -0.55
     Wiktionnaire
    -0.54
    PreferredItem
    -0.54
     professionally
    -0.51
    GEBURTSDATUM
    -0.51
    verwijspagina
    -0.51
    bkz
    -0.50
    POSITIVE LOGITS
     political
    1.00
     physical
    0.96
    political
    0.89
     Political
    0.87
     geological
    0.85
    physical
    0.85
     sexual
    0.84
    Political
    0.83
     POLITICAL
    0.82
     personal
    0.82
    Activations Density 6.743%

    No Known Activations