© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13610
    Prev
    Next
    INDEX
    Explanations

    mentions of family members and concern for people

    oai_token-act-pair · gemini-2.0-flash

    family and love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IntoConstraints
    -0.71
    ########.
    -0.70
     незавершена
    -0.69
     beginnetje
    -0.65
     يتيمه
    -0.61
     Meksiku
    -0.60
    évaluateur
    -0.60
    expandindo
    -0.56
     समीक्षाओं
    -0.55
     lenker
    -0.53
    POSITIVE LOGITS
    ిక
    0.55
     maternelle
    0.55
    featureID
    0.54
    UpdateCommand
    0.50
    Chem
    0.49
    ReferenceEquals
    0.48
    DataAnnotations
    0.48
     utafitiHapana
    0.48
    ızlık
    0.47
     Pneumatic
    0.47
    Activations Density 0.805%

    No Known Activations