© 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. 12480
    Prev
    Next
    INDEX
    Explanations

    SQL syntax including date ranges, `SELECT`, `FROM`, `WHERE`, `ORDER BY`, and table names.

    oai_token-act-pair · gemini-2.0-flash

    database queries

    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
    ValueStyle
    -1.42
     كومونز
    -1.30
    GraphicsUnit
    -1.30
    SharedDtor
    -1.29
     للاسماء
    -1.28
    NameInMap
    -1.27
     resourceCulture
    -1.27
     useAppContext
    -1.22
    rungsseite
    -1.21
    enumi
    -1.20
    POSITIVE LOGITS
     
    0.68
    ,
    0.59
    ↵
    0.57
     o
    0.54
    ↵↵
    0.53
     "
    0.52
     Go
    0.46
     C
    0.46
     m
    0.45
     K
    0.45
    Activations Density 10.781%

    No Known Activations