© 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. 9798
    Prev
    Next
    INDEX
    Explanations

    seemingly random and meaningless characters and formatting

    oai_token-act-pair · gemini-2.0-flash

    Code, math, instructions

    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
     create
    -1.29
     find
    -1.29
     give
    -1.24
     learn
    -1.24
     make
    -1.23
     take
    -1.23
     keep
    -1.22
     apply
    -1.19
     explore
    -1.18
     choose
    -1.17
    POSITIVE LOGITS
     recent
    0.52
     fubject
    0.49
    OutputType
    0.49
    jgl
    0.47
    apimachinery
    0.46
     étoit
    0.46
     mourut
    0.45
     former
    0.45
     sources
    0.42
     background
    0.41
    Activations Density 4.644%

    No Known Activations