© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10188
    Prev
    Next
    INDEX
    Explanations

    the word 'email' in the text, as well as other related terms like 'attachments' and 'content'

    oai_token-act-pair · gemini-2.0-flash

    email

    np_max-act-logits · gemini-2.0-flash
    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
    rungsseite
    -1.11
    ⓧ
    -1.01
    Personensuche
    -0.98
    RegistryLite
    -0.88
    Autoritní
    -0.86
    aarrggbb
    -0.84
     protoimpl
    -0.84
    IVEREF
    -0.82
     ویکی‌پدی
    -0.79
     насељу
    -0.79
    POSITIVE LOGITS
     sent
    1.12
     send
    1.11
     sending
    1.02
     sends
    0.98
     Send
    0.93
    send
    0.93
    Sending
    0.92
    sent
    0.90
     mengirim
    0.88
    Send
    0.87
    Activations Density 4.807%

    No Known Activations