© 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. 13180
    Prev
    Next
    INDEX
    Explanations

    non-English words and programming terms

    oai_token-act-pair · gemini-2.0-flash

    lemp

    np_max-act · gemini-2.0-flash

    ▁

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Not in Any Lists

    No Comments

    Negative Logits
     sula
    -1.05
     tempel
    -1.04
     rivi
    -1.02
     talle
    -0.98
     groen
    -0.97
     kiti
    -0.97
     spion
    -0.97
     alis
    -0.97
     tait
    -0.96
     deri
    -0.95
    POSITIVE LOGITS
    NUMX
    1.38
    ratulations
    1.38
    ercises
    1.34
    iffance
    1.33
     antaranya
    1.30
    elfare
    1.30
     дописавши
    1.30
    ]")]
    1.28
    polation
    1.27
    ſſer
    1.26
    Activations Density 0.926%

    No Known Activations