© 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. 15903
    Prev
    Next
    INDEX
    Explanations

    words related to the government, development, and economics of a local area

    oai_token-act-pair · gemini-2.0-flash

    Business, government, information

    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
     habet
    -0.61
     semula
    -0.60
     feroit
    -0.59
     pisau
    -0.58
     avoient
    -0.55
     Theſe
    -0.55
     perciò
    -0.54
     picioare
    -0.54
     hunne
    -0.54
     religione
    -0.53
    POSITIVE LOGITS
    LookAnd
    0.92
     referrerpolicy
    0.77
    ResponseWriter
    0.73
    UrlResolution
    0.69
    原始内容存档于
    0.68
    oredCriteria
    0.68
     typelib
    0.66
    kuuta
    0.65
     Chwiliwch
    0.64
    Xna
    0.62
    Activations Density 1.955%

    No Known Activations