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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11606
    Prev
    Next
    INDEX
    Explanations

    the word "seeing", and to a lesser extent the words "saw", "see", "sitting", "recreating", "recreating", "much" and "spectator"

    oai_token-act-pair · gemini-2.0-flash

    seeing

    np_max-act · gemini-2.0-flash

    seeing

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     seeing
    -2.22
    seeing
    -2.00
    Seeing
    -1.99
     Seeing
    -1.96
     hearing
    -1.16
    Hearing
    -1.11
    hearing
    -1.04
     Hearing
    -1.00
     увиде
    -0.94
     noticing
    -0.93
    POSITIVE LOGITS
     CreateTagHelper
    0.61
    DateTimeField
    0.59
    
    0.57
    '][$
    0.56
    ++]=
    0.56
    ือ
    0.54
    ennifer
    0.50
    ]=$
    0.50
    anggaran
    0.50
    LEVANT
    0.49
    Activations Density 2.031%

    No Known Activations