© 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. 1767
    Prev
    Next
    INDEX
    Explanations

    a mix of positive sentiment, references to night, and some indication of social unease or outrage

    oai_token-act-pair · gemini-2.0-flash

    recent events

    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
     Yesterday
    -1.29
    Yesterday
    -1.23
     Today
    -1.12
     yesterday
    -1.10
     today
    -1.07
    Today
    -1.06
     tomorrow
    -1.05
    yesterday
    -1.02
     Tomorrow
    -0.98
    Tomorrow
    -0.97
    POSITIVE LOGITS
     last
    1.98
    last
    1.55
    Last
    1.55
     Last
    1.49
     LAST
    1.34
     letzten
    1.23
     último
    1.20
     laatste
    1.20
    ton
    1.20
     terakhir
    1.18
    Activations Density 6.798%

    No Known Activations