© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3449
    Prev
    Next
    INDEX
    Explanations

    the letters "pi" or the name "Giunta"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الرياضيه
    -0.99
    ConstraintMaker
    -0.98
    SourceChecksum
    -0.94
     ویکی‌پدیا
    -0.90
     doInBackground
    -0.85
    awtextra
    -0.85
     snippetHide
    -0.82
    KommentareTeilen
    -0.81
    Geplaatst
    -0.81
     onBackPressed
    -0.81
    POSITIVE LOGITS
    y
    0.56
    ak
    0.51
    am
    0.47
    u
    0.47
    ag
    0.42
    ii
    0.42
    an
    0.40
    ors
    0.40
    ang
    0.39
    ans
    0.39
    Activations Density 0.641%

    No Known Activations