© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16185
    Prev
    Next
    INDEX
    Explanations

    words relating to government/business, health, or finance

    oai_token-act-pair · gemini-2.0-flash

    institutions and professions

    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
     normaux
    -0.76
     élas
    -0.74
     dieux
    -0.71
     feroit
    -0.71
     sauvages
    -0.69
     vicenda
    -0.68
     démocr
    -0.68
     avoient
    -0.68
     firent
    -0.68
     pluie
    -0.68
    POSITIVE LOGITS
    Personendaten
    0.69
     محفوظة
    0.67
    +#+
    0.61
    awtextra
    0.61
    ScopeManager
    0.60
     referenties
    0.60
    thâu
    0.59
     متعلقه
    0.54
    osoba
    0.52
     mes
    0.51
    Activations Density 3.001%

    No Known Activations