© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9595
    Prev
    Next
    INDEX
    Explanations

    mentions of watching, seeing, experiencing or looking at things, often with an additional descriptor of enjoyment or ease.

    oai_token-act-pair · gemini-2.0-flash

    watch/eyes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Mann
    -0.49
    uero
    -0.45
     Bal
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    principalTable
    -0.44
    AndEndTag
    -0.44
     shares
    -0.43
    :
    -0.43
     appContext
    -0.42
     One
    -0.42
    POSITIVE LOGITS
     myſelf
    0.78
     auffi
    0.74
     Jefus
    0.74
     itſelf
    0.72
     visuel
    0.70
     purpoſe
    0.70
    IntoConstraints
    0.69
     sguardo
    0.68
     retina
    0.68
     Monfieur
    0.68
    Activations Density 0.730%

    No Known Activations