© 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. 12255
    Prev
    Next
    INDEX
    Explanations

    code snippets including struct definitions and memory operations like read or write.

    oai_token-act-pair · gemini-2.0-flash

    write or set

    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
     tartalomajánló
    -0.63
    onica
    -0.60
    blings
    -0.58
    letka
    -0.57
    aimana
    -0.55
    mity
    -0.54
    orothy
    -0.54
    resents
    -0.54
     ]
    -0.54
    ISupport
    -0.53
    POSITIVE LOGITS
     AssemblyCulture
    0.68
    complexContent
    0.65
     continúas
    0.58
    GEBURTSDATUM
    0.50
     saites
    0.48
     NSCoder
    0.46
    abestanden
    0.46
     بيها
    0.45
     altrimenti
    0.45
     tratta
    0.43
    Activations Density 0.779%

    No Known Activations