© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6487
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to programming code, particularly in Javascript.

    oai_token-act-pair · gemini-2.0-flash

    pronouns

    np_token-act-pair-logits · gpt-4o-mini

    gendered pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Билгалдахарш
    -0.87
    
    -0.80
     jsPsych
    -0.72
    TextAppearance
    -0.68
     estekak
    -0.68
     OnInit
    -0.68
    ")->
    -0.67
     ControllerBase
    -0.65
     doubtnut
    -0.64
     referenties
    -0.64
    POSITIVE LOGITS
     her
    2.44
     him
    2.36
     she
    2.31
     his
    1.91
    she
    1.73
     hers
    1.69
    她
    1.66
     he
    1.64
    彼女の
    1.59
    She
    1.57
    Activations Density 1.161%

    No Known Activations