© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7357
    Prev
    Next
    INDEX
    Explanations

    somewhat random sequences of letters

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ſelf
    -0.90
     myſelf
    -0.81
     Efq
    -0.81
    wiſe
    -0.80
     uſed
    -0.79
    ſelves
    -0.71
     itſelf
    -0.71
     themſelves
    -0.70
     himſelf
    -0.70
     ſhall
    -0.69
    POSITIVE LOGITS
    ∣
    0.52
    ්
    0.48
    -
    0.45
    ്
    0.44
    Enllaces
    0.44
     surla
    0.44
    ¬
    0.42
    ్
    0.41
    T
    0.40
     geliyor
    0.40
    Activations Density 1.370%

    No Known Activations