© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14746
    Prev
    Next
    INDEX
    Explanations

    conjunctions like "and," correlation words like "both," words about engineering or research like "simulated," and words describing people like "male" and "female."

    oai_token-act-pair · gemini-2.0-flash

    and

    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
     n
    -0.52
     te
    -0.46
     fa
    -0.42
    .
    -0.40
    Well
    -0.39
     (
    -0.39
    ...
    -0.38
    ,
    -0.38
     d
    -0.38
    …
    -0.37
    POSITIVE LOGITS
     للمعارف
    1.11
    tvguidetime
    0.99
    MENAFN
    0.93
     للاسماء
    0.93
    awtextra
    0.90
     pinulongan
    0.90
    UpInside
    0.88
     Efq
    0.87
     autorytatywna
    0.86
     Monfieur
    0.86
    Activations Density 20.979%

    No Known Activations