© 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. 13956
    Prev
    Next
    INDEX
    Explanations

    mathematical and code notations

    oai_token-act-pair · gemini-2.0-flash

    1

    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
     مشين
    -0.79
    CloseOperation
    -0.73
     سكانية
    -0.71
    RenderAtEndOf
    -0.69
    __(/*!
    -0.67
    లాలు
    -0.62
    belea
    -0.60
     resourceCulture
    -0.58
     Exacts
    -0.57
    GEBURTS
    -0.57
    POSITIVE LOGITS
    <bos>
    0.60
     Perſ
    0.55
     AppCompatTheme
    0.54
     offene
    0.54
     offenen
    0.52
     hjælp
    0.52
     Traditional
    0.51
     Diſ
    0.49
    tidaknya
    0.49
     acrylique
    0.49
    Activations Density 4.220%

    No Known Activations