© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13410
    Prev
    Next
    INDEX
    Explanations

    mentions of location and value, specifically in social or personal settings.

    oai_token-act-pair · gemini-2.0-flash

    place

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Monfieur
    -1.17
     myſelf
    -1.16
     Efq
    -1.13
     itſelf
    -1.11
     houſe
    -1.09
     pleaſure
    -1.09
     Shakspeare
    -1.09
     Cæsar
    -1.07
     Houſe
    -1.03
     Jefus
    -1.02
    POSITIVE LOGITS
     N
    0.67
     
    0.64
     ‘
    0.63
     S
    0.63
     us
    0.61
     I
    0.61
     Ber
    0.61
     T
    0.60
     '
    0.59
     It
    0.59
    Activations Density 0.531%

    No Known Activations