© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10147
    Prev
    Next
    INDEX
    Explanations

    words relating to something being used or taken up

    oai_token-act-pair · gemini-2.0-flash

    occupied

    np_max-act · gemini-2.0-flash

    occupied

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     مشين
    -0.80
     فريبيس
    -0.76
    ftagPool
    -0.75
     AssemblyCulture
    -0.73
    aarrggbb
    -0.65
     estekak
    -0.62
     OFDb
    -0.62
    niosek
    -0.60
    '][$
    -0.60
    RenderAtEndOf
    -0.59
    POSITIVE LOGITS
     تضيفلها
    0.63
    getCmp
    0.60
     Trafalgar
    0.60
     ſtate
    0.59
     quæ
    0.58
     Camar
    0.58
     NavController
    0.57
     pleaſure
    0.57
     each
    0.57
    Transcription
    0.57
    Activations Density 1.418%

    No Known Activations