© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12290
    Prev
    Next
    INDEX
    Explanations

    passages expressing the need for something.

    oai_token-act-pair · gemini-2.0-flash

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     need
    -1.27
     Need
    -1.18
     needs
    -1.16
     Needs
    -1.14
    Need
    -1.09
    Needs
    -1.06
    needs
    -1.06
     NEED
    -1.05
    need
    -1.04
     besoin
    -1.00
    POSITIVE LOGITS
     autorytatywna
    0.75
     ejus
    0.66
     disambiguazione
    0.62
     发表于
    0.62
    +:+
    0.61
     itſelf
    0.58
    ſelves
    0.57
     sureties
    0.56
     potest
    0.56
     Fath
    0.56
    Activations Density 23.862%

    No Known Activations