© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11059
    Prev
    Next
    INDEX
    Explanations

    C# code, particularly related to listboxes and data filling

    oai_token-act-pair · gemini-2.0-flash

    application code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Diweddarwch
    -0.78
    zner
    -0.56
     doInBackground
    -0.56
     gabbana
    -0.53
    XmlIgnore
    -0.53
    __':
    -0.52
    XDECREF
    -0.52
    formik
    -0.51
    Makefile
    -0.51
    ябре
    -0.50
    POSITIVE LOGITS
    Band
    0.48
    XmlAccessorType
    0.47
    IsContent
    0.45
     المعيارى
    0.45
     Bands
    0.45
    PreferredItem
    0.45
    tagHelper
    0.44
     Verm
    0.44
     Band
    0.43
     HOP
    0.43
    Activations Density 0.289%

    No Known Activations