© 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. 15671
    Prev
    Next
    INDEX
    Explanations

    connections, such as prepositions and conjunctions, between academic titles and disciplines

    oai_token-act-pair · 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
    mybatisplus
    -1.30
    Datuak
    -0.98
    SBATCH
    -0.93
    SourceChecksum
    -0.93
    sizeCache
    -0.86
     HasFactory
    -0.85
    thâu
    -0.85
    UnitTesting
    -0.84
    μως
    -0.84
     GenerationType
    -0.83
    POSITIVE LOGITS
    R
    0.41
    ab
    0.41
     di
    0.39
     critical
    0.39
    abs
    0.39
    IC
    0.36
     sk
    0.36
    д
    0.36
    н
    0.36
     R
    0.36
    Activations Density 3.108%

    No Known Activations