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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10729
    Prev
    Next
    INDEX
    Explanations

    complex family disputes and relationships

    oai_token-act-pair · gemini-2.0-flash

    interpersonal problems

    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
    photobucket
    -0.47
     ped
    -0.45
     inv
    -0.43
    modelBuilder
    -0.43
    ază
    -0.41
    '/',
    -0.40
    ワイイ
    -0.40
    バター
    -0.39
    坑
    -0.38
     humain
    -0.38
    POSITIVE LOGITS
     MainAxisSize
    0.78
    OGND
    0.77
     يتيمه
    0.73
    GEBURTSDATUM
    0.71
    DockStyle
    0.70
     Мексичка
    0.69
     חיצוניים
    0.69
    Kanpo
    0.68
     AssemblyCompany
    0.68
     infide
    0.67
    Activations Density 3.683%

    No Known Activations