© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11491
    Prev
    Next
    INDEX
    Explanations

    words related to governing bodies, taxes, and nature reserves

    oai_token-act-pair · gemini-2.0-flash

    national park or taxes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     MainAxisSize
    -1.04
    tvguidetime
    -1.04
     utafitiHapana
    -0.99
     surla
    -0.94
    endpush
    -0.86
     CreateTagHelper
    -0.85
    
    -0.85
    findpost
    -0.84
    expandindo
    -0.83
     مشين
    -0.81
    POSITIVE LOGITS
    ulp
    0.44
    TestingModule
    0.41
     spre
    0.41
     profunda
    0.41
     Recherche
    0.38
    delà
    0.36
    Lyon
    0.36
     scand
    0.36
     tarte
    0.36
     Responsibility
    0.35
    Activations Density 2.876%

    No Known Activations