© 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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 2670
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships and interactions with others.

    oai_token-act-pair · gemini-2.0-flash

    relationships and conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    oredCriteria
    -0.62
    DebuggerNonUser
    -0.60
    zwald
    -0.56
    ITIONAL
    -0.56
    melidir
    -0.55
     ***!
    -0.55
     Continuing
    -0.55
    :✨
    -0.53
    apeake
    -0.53
    human
    -0.52
    POSITIVE LOGITS
    <bos>
    1.03
     CreateTagHelper
    0.64
     متعلقه
    0.60
     }))
    0.56
    }))
    
    0.56
     typelib
    0.55
     }}$}
    0.54
    ]));
    
    0.52
    ])){
    0.51
    ]))
    
    0.49
    Activations Density 1.028%

    No Known Activations