© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4855
    Prev
    Next
    INDEX
    Explanations

    words that are related to specific events such as recognition ceremonies and related activities.

    oai_token-act-pair · gemini-2.0-flash

    special

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     special
    -1.04
    special
    -1.00
     Special
    -0.87
    Special
    -0.84
     SPECIAL
    -0.81
     speciali
    -0.80
     speciale
    -0.79
     spécial
    -0.78
     specjal
    -0.74
     especiales
    -0.73
    POSITIVE LOGITS
     houſe
    0.79
     Houſe
    0.73
     doubtnut
    0.73
     Majefty
    0.70
     Reſ
    0.70
    AddTagHelper
    0.68
    ICAGO
    0.68
     ſmall
    0.68
     greateſt
    0.66
     Anſ
    0.64
    Activations Density 15.368%

    No Known Activations