© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 8193
    Prev
    Next
    INDEX
    Explanations

    mathematical division or multiple questions, including square roots, prime factorization and divisibility

    oai_token-act-pair · gemini-2.0-flash

    mathematical operations and factors

    np_token-act-pair-logits · gpt-4o-mini

    divisibility and factors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Transport
    -0.54
    cedent
    -0.54
    transport
    -0.54
    getOut
    -0.51
    WriteAttribute
    -0.51
     Neuros
    -0.50
     للمعارف
    -0.50
     unpacked
    -0.49
    ition
    -0.49
     tục
    -0.49
    POSITIVE LOGITS
     esternos
    0.57
    ollectionView
    0.57
    öglichkeiten
    0.56
    )_/¯
    0.56
     poveznice
    0.55
    }*/
    
    0.54
     pinulongan
    0.54
    ')],
    0.52
    luo
    0.51
    }`}
    0.50
    Activations Density 4.820%

    No Known Activations