© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13690
    Prev
    Next
    INDEX
    Explanations

    acronyms, especially related to sports and medicine

    oai_token-act-pair · gemini-2.0-flash

    SON

    np_max-act-logits · gemini-2.0-flash

    ▁CON

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IBOutlet
    -0.63
    ReusableCell
    -0.60
     Rend
    -0.60
    EndProject
    -0.58
     Buena
    -0.57
    PERTIES
    -0.57
    gestone
    -0.56
    ierend
    -0.56
    BorderFactory
    -0.56
    MERCIAL
    -0.55
    POSITIVE LOGITS
     stället
    0.47
     cioè
    0.43
    visející
    0.42
    ConstraintMaker
    0.39
     quæ
    0.39
     indipendente
    0.38
     habet
    0.38
     hubiese
    0.38
     daß
    0.38
    )’
    0.37
    Activations Density 1.731%

    No Known Activations