© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6464
    Prev
    Next
    INDEX
    Explanations

    words that describe negative or unpleasant things or emotional states

    oai_token-act-pair · gemini-2.0-flash

    wob

    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
     provisional
    -0.54
    NamedQuery
    -0.53
     Civil
    -0.52
     art
    -0.52
     civil
    -0.52
     Mota
    -0.52
     Saito
    -0.52
    indakan
    -0.52
    embatan
    -0.52
    rafts
    -0.52
    POSITIVE LOGITS
     betweenstory
    0.69
    WebElementEntity
    0.66
     ویکی‌پدی
    0.56
    AndEndTag
    0.54
    DrawerToggle
    0.52
    ViewFeatures
    0.50
    RenderAtEndOf
    0.50
    glClear
    0.47
    ñera
    0.47
     laiton
    0.45
    Activations Density 8.540%

    No Known Activations