© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6725
    Prev
    Next
    INDEX
    Explanations

    Java code related to persistence

    oai_token-act-pair · gemini-2.0-flash

    Java framework components and attributes

    np_token-act-pair-logits · gpt-4o-mini

    swing package imports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    EndTag
    -0.54
    ashi
    -0.53
    vited
    -0.52
     asli
    -0.50
    orated
    -0.50
    tology
    -0.48
     Original
    -0.48
     fièvre
    -0.47
    chable
    -0.47
    utations
    -0.46
    POSITIVE LOGITS
     Naming
    0.65
    ScopeManager
    0.65
    Referencies
    0.58
    Становништво
    0.55
    clusal
    0.54
     Autorisations
    0.54
    ollectionView
    0.52
    цездатний
    0.52
    Naming
    0.52
    adaptiveStyles
    0.51
    Activations Density 0.076%

    No Known Activations