© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1341
    Prev
    Next
    INDEX
    Explanations

    the word "Sand" followed by another capitalized word

    oai_token-act-pair · gemini-2.0-flash

    Place names with "Sand"

    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
     Мексичка
    -0.88
     tartalomajánló
    -0.83
     '\\;'
    -0.82
    LookAnd
    -0.78
     оригіналу
    -0.77
    GEBURTSDATUM
    -0.76
     виправивши
    -0.76
    parsedMessage
    -0.73
     initComponents
    -0.70
     "..\..\
    -0.69
    POSITIVE LOGITS
    oria
    0.50
    an
    0.48
    t
    0.48
    ales
    0.41
     O
    0.41
    l
    0.40
     off
    0.40
    oo
    0.39
    ar
    0.39
    ry
    0.39
    Activations Density 0.833%

    No Known Activations