© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12205
    Prev
    Next
    INDEX
    Explanations

    words related to technical devices and specific geopolitical concerns

    oai_token-act-pair · gemini-2.0-flash

    safety and mechanics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ViewFeatures
    -0.53
     Extragalactic
    -0.51
    URB
    -0.51
     pinulongan
    -0.50
    djangoproject
    -0.49
    ellery
    -0.49
    itorious
    -0.48
    styleType
    -0.48
    archiviato
    -0.48
     EPR
    -0.47
    POSITIVE LOGITS
    DoubleQuotes
    0.58
    Географи
    0.56
     branche
    0.54
    thâu
    0.53
    ágok
    0.52
    iastes
    0.52
     HasFactory
    0.52
    かというと
    0.51
    SequentialGroup
    0.50
     للمعارف
    0.50
    Activations Density 2.070%

    No Known Activations