© 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. 11133
    Prev
    Next
    INDEX
    Explanations

    a wide variety of short symbols, phrases and acronyms, including those related to biological studies and spreadsheets.

    oai_token-act-pair · gemini-2.0-flash

    Plans, options, appendices

    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
     يتيمه
    -1.16
    Personensuche
    -1.07
    MigrationBuilder
    -1.05
     الحره
    -1.00
    ChildScrollView
    -0.98
     Efq
    -0.96
     незавершена
    -0.93
    Personendaten
    -0.92
     Monfieur
    -0.90
     Jefus
    -0.90
    POSITIVE LOGITS
     B
    2.23
     C
    1.96
    B
    1.83
     D
    1.77
     A
    1.70
    C
    1.55
    D
    1.39
     E
    1.33
    A
    1.28
     b
    1.27
    Activations Density 12.638%

    No Known Activations