© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15498
    Prev
    Next
    INDEX
    Explanations

    names of burial monuments and natural land features, especially mountains and trails

    oai_token-act-pair · gemini-2.0-flash

    mountain-related activities or terms

    np_token-act-pair-logits · gpt-4o-mini

    mountain or hill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     gyhoeddwyd
    -0.65
    AutoScaleMode
    -0.62
     vPvB
    -0.60
    Välislingid
    -0.60
     democrática
    -0.59
    parency
    -0.56
    Parcelize
    -0.55
     JpaRepository
    -0.55
     nắp
    -0.54
    
    -0.54
    POSITIVE LOGITS
    )++;
    0.66
     climber
    0.64
    PyExc
    0.57
    /*
    0.53
     climbers
    0.52
    Ũ
    0.51
     climbing
    0.50
     Roskov
    0.49
    */;
    0.48
    climbing
    0.48
    Activations Density 0.814%

    No Known Activations