© 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. 1023
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly those referring to periods of time or quantity

    oai_token-act-pair · gemini-2.0-flash

    say time units

    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
     Muda
    -0.56
    новништво
    -0.54
     Ages
    -0.53
    جغرافيا
    -0.52
    PyTuple
    -0.52
    ouren
    -0.51
    openqa
    -0.50
     hemo
    -0.50
     three
    -0.50
    naco
    -0.49
    POSITIVE LOGITS
    ंदीखरीदारी
    0.80
    Aholisi
    0.57
    الإنجليزية
    0.56
    φάλ
    0.56
     onCreateView
    0.52
    chave
    0.48
    /**
    0.47
    SPATH
    0.47
     själ
    0.46
    Hochspringen
    0.46
    Activations Density 2.558%

    No Known Activations