© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12403
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets including the words "let const expect"

    oai_token-act-pair · gemini-2.0-flash

    Code/tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     ddelweddau
    -1.01
     الرياضيه
    -0.87
    thâu
    -0.83
    balleur
    -0.82
     Paglinawan
    -0.80
    ,:);
    -0.78
    InitVars
    -0.77
     kasarigan
    -0.74
    )];
    -0.74
    ніципа
    -0.73
    POSITIVE LOGITS
    ResumeLayout
    0.52
     likely
    0.50
    ┏
    0.49
     restera
    0.46
     here
    0.46
    likely
    0.45
    쪽
    0.45
     tabac
    0.45
     Maybe
    0.44
    存于互联网档案馆
    0.44
    Activations Density 1.802%

    No Known Activations