© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9736
    Prev
    Next
    INDEX
    Explanations

    various tokens related to SSL configuration.

    oai_token-act-pair · gemini-2.0-flash

    server configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    /**
    -0.84
     onCreateView
    -0.73
    afficheront
    -0.70
    adpleegd
    -0.64
    SPATH
    -0.62
     Meksiku
    -0.61
    DebuggerNonUser
    -0.60
    invokeLater
    -0.60
    INSEE
    -0.60
     disambiguazione
    -0.59
    POSITIVE LOGITS
     Perſ
    0.61
     Efq
    0.60
     ſche
    0.56
     poffible
    0.55
     Reſ
    0.55
     Monfieur
    0.55
     itſelf
    0.54
     Conſ
    0.53
     faſt
    0.53
     ſta
    0.53
    Activations Density 1.581%

    No Known Activations