© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9904
    Prev
    Next
    INDEX
    Explanations

    the word "part," as well as related concepts like "component", "role", "consequence," and "features".

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    amphetamine
    -0.59
     geluk
    -0.54
     aéri
    -0.52
    miento
    -0.52
    ั้น
    -0.49
     pregunt
    -0.49
     réguli
    -0.48
     Sigue
    -0.48
    XtraGrid
    -0.48
     algu
    -0.48
    POSITIVE LOGITS
     المعيارى
    0.73
    舺
    0.66
    íncia
    0.66
    opsida
    0.62
    ]<<"
    0.61
    částí
    0.61
    dientemente
    0.61
     estimés
    0.59
     pageContext
    0.57
    клопе
    0.56
    Activations Density 0.863%

    No Known Activations