© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15684
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and punctuation that are specific to mathematical and technical documentation, and also code

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    TagMode
    -0.54
     umana
    -0.52
     باخ
    -0.50
    ırl
    -0.50
     humana
    -0.49
    σύ
    -0.48
     humaine
    -0.48
     presumed
    -0.47
    ثمان
    -0.47
    至今
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.57
    PreAuthorize
    0.53
     knex
    0.52
    ButtonModule
    0.52
    enged
    0.52
    üyada
    0.52
    RTDA
    0.51
     ExecuteAsync
    0.51
    minecraft
    0.50
     onAnimation
    0.50
    Activations Density 9.751%

    No Known Activations