© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7286
    Prev
    Next
    INDEX
    Explanations

    words in subjective sentences about feelings

    oai_token-act-pair · gemini-2.0-flash

    needs and wants

    np_max-act-logits · gemini-2.0-flash

    need

    np_max-act-logits · gpt-5-mini
    Triggered 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
    Negative Logits
     photolibrary
    -0.83
    ^(@)
    -0.83
     iſt
    -0.80
    tvguidetime
    -0.80
     EconPapers
    -0.78
     ſind
    -0.77
     展板
    -0.77
     myſelf
    -0.76
     houſe
    -0.75
     Efq
    -0.74
    POSITIVE LOGITS
     in
    0.73
    .
    0.69
     on
    0.67
     from
    0.62
     for
    0.62
    ,
    0.60
     to
    0.53
    ContentLoaded
    0.52
    :
    0.51
     we
    0.49
    Activations Density 55.247%

    No Known Activations