© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5375
    Prev
    Next
    INDEX
    Explanations

    code-like text, especially of Vietnamese origin, and html-looking things

    oai_token-act-pair · gemini-2.0-flash

    Programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     houſe
    -1.24
     ſtate
    -1.22
     pleaſure
    -1.20
     raiſ
    -1.17
     ſmall
    -1.16
     ſever
    -1.15
     ſtre
    -1.14
     purpoſe
    -1.13
     perſon
    -1.11
     diſt
    -1.09
    POSITIVE LOGITS
     bidang
    0.25
     An
    0.25
     preuves
    0.24
     sinais
    0.24
     quaisquer
    0.24
     perilaku
    0.23
     logiciels
    0.23
     an
    0.22
     vectorielles
    0.22
     A
    0.22
    Activations Density 0.277%

    No Known Activations