© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14477
    Prev
    Next
    INDEX
    Explanations

    passages about legal situations, especially those involving cancellation and evidence

    oai_token-act-pair · gemini-2.0-flash

    retracting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ),),
    -0.52
    sizeCache
    -0.50
     createContext
    -0.49
    WithFormat
    -0.48
    idées
    -0.46
     Presidente
    -0.46
     fusi
    -0.45
    Ė
    -0.45
    Causas
    -0.45
    burton
    -0.45
    POSITIVE LOGITS
    webElementXpaths
    0.73
     typelib
    0.66
     tartalomajánló
    0.63
     retirer
    0.63
     Signalez
    0.62
     paraître
    0.58
    nloa
    0.56
    transQ
    0.56
    ractable
    0.54
     sanitaire
    0.54
    Activations Density 1.416%

    No Known Activations