© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11376
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing

    oai_token-act-pair · gemini-2.0-flash

    Clothing and error messages

    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
     nahilalakip
    -1.11
    SourceChecksum
    -0.99
    +#+
    -0.98
     Roskov
    -0.96
    tagHelperRunner
    -0.90
     ***!
    -0.90
    клопе
    -0.90
     AssemblyCulture
    -0.87
    oa̍t
    -0.84
    bootstrapcdn
    -0.83
    POSITIVE LOGITS
    ëren
    0.52
     set
    0.45
    hidden
    0.42
    邃
    0.40
     hidden
    0.40
     sweep
    0.38
     
    0.38
    set
    0.37
    ല്ല
    0.37
    build
    0.37
    Activations Density 0.392%

    No Known Activations