© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11186
    Prev
    Next
    INDEX
    Explanations

    text enclosed with some special characters like * and brackets

    oai_token-act-pair · gemini-2.0-flash

    Asterisks

    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
     religieuses
    -0.77
     énergé
    -0.70
     chré
    -0.70
     jeter
    -0.70
    tagHelperRunner
    -0.67
     purpoſe
    -0.66
    addGap
    -0.65
     fubject
    -0.64
    անո
    -0.63
     avoient
    -0.63
    POSITIVE LOGITS
    ConstraintMaker
    0.67
     autorytatywna
    0.67
    */,
    0.63
    </i>
    0.57
    `]
    0.52
     >=",
    0.51
    ParallelGroup
    0.50
     typical
    0.50
    ']}
    0.49
    </em>
    0.49
    Activations Density 1.157%

    No Known Activations