© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9684
    Prev
    Next
    INDEX
    Explanations

    words related to event planning, records and organized data.

    oai_token-act-pair · gemini-2.0-flash

    Project management

    np_max-act-logits · gemini-2.0-flash

    events

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ècie
    -0.50
     متعلقه
    -0.47
     atardecer
    -0.43
     pula
    -0.43
     compréhen
    -0.40
    Geplaatst
    -0.40
    enschappelijke
    -0.40
     cielos
    -0.40
    rvore
    -0.39
     peor
    -0.39
    POSITIVE LOGITS
     насељу
    0.73
     Majefty
    0.69
     itſelf
    0.68
     myſelf
    0.68
    ſelf
    0.66
     cauſe
    0.63
    Portály
    0.62
    Datuak
    0.62
     ſche
    0.62
     betweenstory
    0.62
    Activations Density 8.811%

    No Known Activations