© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16140
    Prev
    Next
    INDEX
    Explanations

    references to academic classes or social class

    oai_token-act-pair · gemini-2.0-flash

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     class
    -1.40
    class
    -1.16
     Class
    -0.73
    Class
    -0.72
     very
    -0.67
     more
    -0.67
     a
    -0.66
     procu
    -0.62
    クラス
    -0.61
     classes
    -0.60
    POSITIVE LOGITS
    principalColumn
    1.02
    UnusedPrivate
    0.99
     صوتيه
    0.98
     disambiguazione
    0.96
     ModelExpression
    0.91
    MigrationBuilder
    0.91
     Paglinawan
    0.90
    webElementXpaths
    0.89
    MemoryWarning
    0.87
    SourceChecksum
    0.86
    Activations Density 1.626%

    No Known Activations