© 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. 14102
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sales and marketing

    oai_token-act-pair · gemini-2.0-flash

    Marketing, possibly in Russian

    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
     avoient
    -1.50
     Efq
    -1.45
     feroit
    -1.35
     Theſe
    -1.35
     auroit
    -1.34
     étoient
    -1.34
     Monfieur
    -1.30
     quelcon
    -1.30
     pouvoit
    -1.28
     réguli
    -1.27
    POSITIVE LOGITS
    ,
    1.00
     to
    0.96
    y
    0.87
    es
    0.86
    en
    0.82
    or
    0.82
    -
    0.81
    o
    0.80
     up
    0.79
    _
    0.78
    Activations Density 2.187%

    No Known Activations