© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9434
    Prev
    Next
    INDEX
    Explanations

    long sentence fragments with the word "well" and other words describing communication or providing a service or link

    oai_token-act-pair · gemini-2.0-flash

    Clarification or providing a service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    </blockquote>
    -0.46
     hod
    -0.41
     in
    -0.37
    </strong>
    -0.37
     kê
    -0.36
    <eos>
    -0.35
     falou
    -0.35
     from
    -0.35
     u
    -0.35
     In
    -0.35
    POSITIVE LOGITS
    Personendaten
    1.23
     myſelf
    1.19
     Efq
    1.17
     Majefty
    1.15
     houſe
    1.13
    ſelves
    1.10
     itſelf
    1.09
     Houſe
    1.09
     Anſ
    1.06
    ſelf
    1.05
    Activations Density 0.723%

    No Known Activations