© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack of intention or disagreement

    oai_token-act-pair · gemini-2.0-flash

    technical/legal texts

    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
    бият
    -0.58
    ophyllum
    -0.54
     nakalista
    -0.53
    iteiten
    -0.50
     Hauses
    -0.50
     Happen
    -0.50
    asserole
    -0.49
     DIOS
    -0.49
     Chakra
    -0.49
     Estar
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.69
     DESIGN
    0.57
     design
    0.57
    Hochspringen
    0.57
     متعلقه
    0.57
    DESIGN
    0.55
    protoimpl
    0.55
     Drapeau
    0.55
     Design
    0.54
    design
    0.54
    Activations Density 1.070%

    No Known Activations