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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15992
    Prev
    Next
    INDEX
    Explanations

    proper nouns and terms related to auditing, finance, and business

    oai_token-act-pair · gemini-2.0-flash

    company audit firms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pinulongan
    -0.84
    #
    -0.83
    WriteTagHelper
    -0.68
     esternos
    -0.67
     ProtoMessage
    -0.65
     initComponents
    -0.65
     مشين
    -0.65
     урна
    -0.63
    writeFieldEnd
    -0.63
    Geplaatst
    -0.62
    POSITIVE LOGITS
     vPvB
    0.52
    PendingIntent
    0.50
    sendRedirect
    0.47
    formin
    0.41
     nameof
    0.40
    PickerController
    0.39
    viewDidLoad
    0.38
    తు
    0.38
    cerely
    0.37
    igshid
    0.37
    Activations Density 2.681%

    No Known Activations