© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1831
    Prev
    Next
    INDEX
    Explanations

    scientific writing describing experiments/methodologies

    oai_token-act-pair · gemini-2.0-flash

    using

    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
     using
    -1.81
    Using
    -1.46
     Using
    -1.46
    using
    -1.41
     USING
    -1.28
     menggunakan
    -1.28
     utilizando
    -1.23
     usando
    -1.16
     utilizzando
    -1.09
     utilisant
    -1.06
    POSITIVE LOGITS
     propOrder
    1.24
     CreateTagHelper
    1.00
     ContentValues
    0.98
    awtextra
    0.97
     resourceCulture
    0.94
     onPostExecute
    0.94
     defaultstate
    0.93
    Datuak
    0.93
    تقاوى
    0.90
    NUMX
    0.88
    Activations Density 5.725%

    No Known Activations