© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4181
    Prev
    Next
    INDEX
    Explanations

    mentions of computing clients

    oai_token-act-pair · gemini-2.0-flash

    client

    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
     client
    -2.66
     clients
    -2.44
    client
    -2.39
     Client
    -2.33
    Client
    -2.30
     Clients
    -2.30
    Clients
    -2.09
    clients
    -2.03
     CLIENT
    -1.97
    CLIENT
    -1.91
    POSITIVE LOGITS
    TargetException
    0.64
    BindingSource
    0.47
     الحره
    0.47
     Потому
    0.47
    DebuggerNonUser
    0.47
     Viter
    0.45
     imprimi
    0.45
     baterai
    0.44
    TextAppearance
    0.43
     sesso
    0.43
    Activations Density 1.557%

    No Known Activations