© 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. 14621
    Prev
    Next
    INDEX
    Explanations

    the word "key" or "keys", especially in the context of buttons, presses, values or configuration.

    oai_token-act-pair · gemini-2.0-flash

    key

    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
     quæ
    -0.66
     betweenstory
    -0.58
     Jefus
    -0.58
     myſelf
    -0.58
     Efq
    -0.57
     Públicas
    -0.56
     Theſe
    -0.56
     Monfieur
    -0.54
    ientí
    -0.53
    ressee
    -0.53
    POSITIVE LOGITS
    forChild
    0.62
    setVerticalGroup
    0.62
    interopRequire
    0.57
    xase
    0.55
    migrationBuilder
    0.54
     الرخصة
    0.54
    })();
    0.52
    StoreMessageInfo
    0.51
    MessageTagHelper
    0.50
    atguigu
    0.50
    Activations Density 2.107%

    No Known Activations