© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    various words with different meanings, with no single discernible topic.

    oai_token-act-pair · gemini-2.0-flash

    Questions or references

    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
     anyone
    -2.30
     anything
    -2.30
     Anything
    -2.27
    anything
    -2.23
    anyone
    -2.19
    Anything
    -2.17
     Anyone
    -2.16
     Anybody
    -2.11
    Anyone
    -2.09
     anybody
    -2.05
    POSITIVE LOGITS
     tout
    0.86
    mybatisplus
    0.53
    windowFixed
    0.49
    ✨:
    0.49
    ulatum
    0.48
     ")");
    0.48
    brough
    0.47
    ^(@)
    0.47
     Brabant
    0.47
     spur
    0.47
    Activations Density 4.291%

    No Known Activations