© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14223
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially in languages like Javascript or PHP, possibly related to web development or game programming

    oai_token-act-pair · gemini-2.0-flash

    code variables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     la
    -0.82
     le
    -0.78
     el
    -0.73
     l
    -0.68
     And
    -0.65
     me
    -0.64
     Or
    -0.63
     qu
    -0.62
     r
    -0.60
     The
    -0.59
    POSITIVE LOGITS
     pleaſure
    0.91
     ſever
    0.81
     itſelf
    0.80
     Cæsar
    0.77
     myſelf
    0.77
     Thebes
    0.77
     Monfieur
    0.77
     ſche
    0.75
     dafs
    0.74
     purpoſe
    0.73
    Activations Density 5.374%

    No Known Activations