© 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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13425
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with computers, electronics, or technology AND also words associated with mistakes

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    enumii
    -0.73
    EDEFAULT
    -0.71
    enumi
    -0.69
     jScrollPane
    -0.67
    CppMethod
    -0.63
    TestingModule
    -0.60
    EnableWeb
    -0.59
    ⓧ
    -0.59
     NgModule
    -0.58
    httphttps
    -0.58
    POSITIVE LOGITS
     there
    1.40
     here
    1.30
     allí
    1.19
    在那里
    1.15
     там
    1.13
     dort
    1.12
     ahí
    1.11
     acolo
    1.09
    there
    1.09
     thither
    0.99
    Activations Density 1.524%

    No Known Activations