© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7917
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, math formulas and URLs, especially those associated with audio and video content

    oai_token-act-pair · gemini-2.0-flash

    code/markup

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SharedCtor
    -0.86
    AddTagHelper
    -0.82
     HasFactory
    -0.78
    matchCondition
    -0.75
    djangoproject
    -0.75
    __':
    -0.74
    Personensuche
    -0.73
     الحره
    -0.73
    ).__
    -0.71
     مرئيه
    -0.70
    POSITIVE LOGITS
     Mosley
    0.60
     RAC
    0.57
     Boucher
    0.56
     couch
    0.54
     Tenth
    0.54
    Couch
    0.53
     Kram
    0.52
     NIT
    0.51
     giraffe
    0.51
     Vitale
    0.50
    Activations Density 5.036%

    No Known Activations