© 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. 12657
    Prev
    Next
    INDEX
    Explanations

    sentences with pronouns and contractions

    oai_token-act-pair · gemini-2.0-flash

    everyday activities

    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
     ModelExpression
    -0.76
     समीक्षाओं
    -0.66
     للمعارف
    -0.65
     nakalista
    -0.61
    참고
    -0.60
    发表于
    -0.58
    twimg
    -0.56
     utafitiHapana
    -0.56
    WireFormatLite
    -0.55
    ⓧ
    -0.55
    POSITIVE LOGITS
    serviceWorker
    0.51
    hala
    0.50
    ady
    0.48
    </thead>
    0.48
    hena
    0.47
    mary
    0.46
    esz
    0.46
     break
    0.46
     run
    0.46
    makeConstraints
    0.45
    Activations Density 2.854%

    No Known Activations