© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9550
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, annotations, and syntax elements, especially focusing on Java or similar languages

    oai_token-act-pair · gemini-2.0-flash

    boolean values

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     volontaire
    -0.50
     fossero
    -0.48
     européennes
    -0.47
    сів
    -0.47
    weite
    -0.44
    hould
    -0.44
     jutaan
    -0.44
     sehari
    -0.44
     длина
    -0.44
     bäst
    -0.43
    POSITIVE LOGITS
     yes
    0.85
    bool
    0.83
     Yes
    0.82
     bool
    0.82
    findpost
    0.77
     whether
    0.76
    Yes
    0.75
    whether
    0.75
     Whether
    0.74
    Whether
    0.74
    Activations Density 0.423%

    No Known Activations