© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14573
    Prev
    Next
    INDEX
    Explanations

    institutions that have to do with medicine and are in India

    oai_token-act-pair · gemini-2.0-flash

    Code, foreign languages, Narasimha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    NewUrlParser
    -0.54
     Normdatei
    -0.53
    AccessorTable
    -0.51
    __(/*!
    -0.48
     AssemblyCulture
    -0.46
     doInBackground
    -0.46
     Motley
    -0.43
    setLayoutManager
    -0.43
    uxxxx
    -0.42
     referenties
    -0.42
    POSITIVE LOGITS
     насељу
    0.69
    elemField
    0.65
    SystemColors
    0.62
    KEYCODE
    0.60
    Spoljašnje
    0.59
    zzar
    0.57
    homonymie
    0.57
    SuspendLayout
    0.57
    ToLeft
    0.57
    حياته
    0.56
    Activations Density 0.627%

    No Known Activations