© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4411
    Prev
    Next
    INDEX
    Explanations

    phrases about spending time, especially quality time, with family

    oai_token-act-pair · gemini-2.0-flash

    quality or free time

    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
     Theſe
    -0.71
     createState
    -0.71
     ſeveral
    -0.67
     Jefus
    -0.66
     myſelf
    -0.65
     whoſe
    -0.62
     beſ
    -0.60
     Monfieur
    -0.60
    SpringBoot
    -0.59
     Beſ
    -0.58
    POSITIVE LOGITS
     down
    1.67
     Down
    1.44
    Down
    1.38
    down
    1.37
     DOWN
    1.31
    DOWN
    1.21
    downs
    1.02
    ダウン
    0.88
     downs
    0.85
     off
    0.81
    Activations Density 2.694%

    No Known Activations