© 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. 13208
    Prev
    Next
    INDEX
    Explanations

    sequences of letters and symbols that often occur in computer code or math equations

    oai_token-act-pair · gemini-2.0-flash

    code or math

    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
    providedIn
    -0.68
    GraphicsUnit
    -0.67
    出版年
    -0.66
    posedge
    -0.63
     rospy
    -0.62
    الإنجليزية
    -0.60
    ophora
    -0.59
     propOrder
    -0.59
    sendFile
    -0.59
    GEBURTSDATUM
    -0.58
    POSITIVE LOGITS
    oa̍t
    0.48
     itſelf
    0.47
    tonode
    0.44
     Carta
    0.44
     Nightingale
    0.44
     muſt
    0.44
    tdessen
    0.44
    Herzliche
    0.43
     predeceased
    0.42
    aryen
    0.42
    Activations Density 4.954%

    No Known Activations