© 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. 9842
    Prev
    Next
    INDEX
    Explanations

    names of people, places and companies, especially with unusual character combinations

    oai_token-act-pair · gemini-2.0-flash

    scientific/academic texts

    np_max-act · gemini-2.0-flash
    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
    Card
    -0.46
    úly
    -0.45
     karşı
    -0.44
     protetor
    -0.44
    шки
    -0.44
    pellier
    -0.42
     getItemId
    -0.42
    livia
    -0.42
     Зо
    -0.42
    āla
    -0.42
    POSITIVE LOGITS
     مشين
    1.04
     Савезне
    0.80
     Infórmanos
    0.79
     صوتيه
    0.75
    NameInMap
    0.75
     viewType
    0.75
    onAttach
    0.75
    NUMX
    0.74
    ///</
    0.73
     estekak
    0.69
    Activations Density 0.162%

    No Known Activations