© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8159
    Prev
    Next
    INDEX
    Explanations

    verbose and filler words such as "a", "the", "of", "in", "to", "with", "that", "is", "be"

    oai_token-act-pair · gemini-2.0-flash

    Science research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Slightly
    -1.03
    highly
    -1.03
     slightly
    -1.01
    Highly
    -0.99
     Highly
    -0.99
     highly
    -0.98
    slightly
    -0.93
    Slightly
    -0.93
     heavily
    -0.90
    completely
    -0.88
    POSITIVE LOGITS
     EconPapers
    0.66
     Efq
    0.62
    ClientSize
    0.57
    InvalidProtocol
    0.56
     unread
    0.56
    AutoScaleMode
    0.56
     protoimpl
    0.55
     astronaut
    0.54
     pleaſure
    0.54
    explique
    0.53
    Activations Density 9.851%

    No Known Activations