© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8154
    Prev
    Next
    INDEX
    Explanations

    mentions of personal preferences or desires

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     slutet
    -0.53
     fjor
    -0.52
     menyen
    -0.52
     början
    -0.51
     fédé
    -0.51
     täv
    -0.50
     tilbage
    -0.49
     tiroirs
    -0.48
     mulighed
    -0.48
     laaj
    -0.47
    POSITIVE LOGITS
     your
    0.67
     seus
    0.65
     seu
    0.64
    Seu
    0.60
    mêmes
    0.59
     своих
    0.59
     свої
    0.57
     свой
    0.56
     swoich
    0.56
     ihren
    0.55
    Activations Density 0.615%

    No Known Activations