© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6431
    Prev
    Next
    INDEX
    Explanations

    the word "total" followed by some sort of qualifier

    oai_token-act-pair · gemini-2.0-flash

    total

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    WebVitals
    -1.41
    parsedMessage
    -1.40
    ^(@)
    -1.39
    yntaxException
    -1.38
    featureID
    -1.38
     nahilalakip
    -1.37
     سكانية
    -1.34
     snippetHide
    -1.33
     lenker
    -1.33
     beginnetje
    -1.32
    POSITIVE LOGITS
    2
    1.23
    1
    1.19
    3
    1.11
    0
    1.11
    4
    1.05
    8
    1.03
    5
    1.02
    6
    0.97
    7
    0.96
    s
    0.93
    Activations Density 2.579%

    No Known Activations