© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12090
    Prev
    Next
    INDEX
    Explanations

    terminology related to antibodies, serology, and other biological assays

    oai_token-act-pair · gemini-2.0-flash

    antibodies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     purpoſe
    -0.83
     whoſe
    -0.81
     myſelf
    -0.79
     pleaſure
    -0.78
     themſelves
    -0.77
     كومونز
    -0.74
     Anſ
    -0.73
    \{\\
    -0.73
     ſeveral
    -0.73
     ſmall
    -0.72
    POSITIVE LOGITS
    TagHelper
    0.48
     Co
    0.44
    +:+
    0.41
     CO
    0.40
     tủ
    0.40
    HttpDelete
    0.40
     mener
    0.39
     ComVisible
    0.38
    deckung
    0.38
     Sch
    0.37
    Activations Density 1.666%

    No Known Activations