© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14578
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially javascript and PHP, including conditional statements, function calls, and database queries

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     comunale
    -0.60
     contemporaine
    -0.59
     écrivain
    -0.57
     Stronger
    -0.56
    more
    -0.56
     armées
    -0.55
     médecins
    -0.54
     créations
    -0.54
     stronger
    -0.52
     enfans
    -0.52
    POSITIVE LOGITS
    rungsseite
    0.84
    expandindo
    0.75
    bewerken
    0.70
     ExecuteAsync
    0.70
    SharedDtor
    0.69
     Exacts
    0.68
     Roskov
    0.68
    +#+#
    0.67
    tagHelperRunner
    0.67
     <<<<<<<<<<<<<<
    0.64
    Activations Density 6.908%

    No Known Activations