© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6868
    Prev
    Next
    INDEX
    Explanations

    words related to bodies, especially sex or babies

    oai_token-act-pair · gemini-2.0-flash

    Describing qualities

    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
     supérieurs
    -0.86
     figliu
    -0.79
     religione
    -0.75
     enfans
    -0.75
     démocr
    -0.74
     dignité
    -0.74
     démocratie
    -0.73
     république
    -0.73
     giustizia
    -0.72
     eenig
    -0.71
    POSITIVE LOGITS
    twimg
    0.72
     AssemblyProduct
    0.69
    )))));
    0.62
    ChildScrollView
    0.61
     [*]
    0.61
    abstractmethod
    0.60
    Ĭ
    0.60
    )];
    0.60
    :✨
    0.59
    rungsseite
    0.59
    Activations Density 15.651%

    No Known Activations