© 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. 7072
    Prev
    Next
    INDEX
    Explanations

    language about action plans on political issues

    oai_token-act-pair · gemini-2.0-flash

    climate

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.67
    oredCriteria
    -0.57
     referenties
    -0.56
    cemment
    -0.53
     الحره
    -0.52
    insee
    -0.52
     garçons
    -0.50
     associés
    -0.49
     Component
    -0.49
    onResume
    -0.47
    POSITIVE LOGITS
     climate
    0.71
     resourceCulture
    0.68
     BoxDecoration
    0.68
     InputDecoration
    0.64
    TagHelper
    0.63
    climate
    0.61
     deforestation
    0.60
    mybatisplus
    0.59
    ázaro
    0.57
     societies
    0.56
    Activations Density 8.361%

    No Known Activations