© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    the word "baby" and words that sometimes go along with it

    oai_token-act-pair · gemini-2.0-flash

    baby

    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
     myſelf
    -1.05
     Anſ
    -0.98
     themſelves
    -0.96
    esgue
    -0.94
     Majefty
    -0.93
     Monfieur
    -0.93
     itſelf
    -0.93
    ſelves
    -0.90
     Efq
    -0.88
    enumi
    -0.87
    POSITIVE LOGITS
    binant
    0.40
    PSON
    0.40
     Процитовано
    0.40
     zur
    0.39
     te
    0.39
     hold
    0.39
     E
    0.38
     gran
    0.38
     fra
    0.38
     Te
    0.37
    Activations Density 0.959%

    No Known Activations