© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11414
    Prev
    Next
    INDEX
    Explanations

    code snippets or documentation, particularly those which contain the abbreviations "id" or "ID"

    oai_token-act-pair · gemini-2.0-flash

    code/data identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    :✨
    -0.59
    Locations
    -0.47
    ITIES
    -0.46
    Jz
    -0.45
     Lakes
    -0.45
     thirsty
    -0.45
    bjs
    -0.44
     Hartley
    -0.44
    気がします
    -0.43
    ox
    -0.42
    POSITIVE LOGITS
     nakalista
    0.72
    下载附件
    0.71
    
    0.65
     pinulongan
    0.65
    berdayakan
    0.64
    sidemargin
    0.63
     contextLoads
    0.60
    BufferException
    0.58
     jScrollPane
    0.58
     Axiom
    0.56
    Activations Density 24.303%

    No Known Activations