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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15065
    Prev
    Next
    INDEX
    Explanations

    C++ code, potentially related to testing and configuration

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    -0.52
     AttributeError
    -0.48
     EdgeInsets
    -0.47
     Commentaires
    -0.45
    Geographie
    -0.45
    ண்டு
    -0.44
    كامل
    -0.44
    Geografie
    -0.44
     rê
    -0.43
    MultipartFile
    -0.42
    POSITIVE LOGITS
    oredCriteria
    0.90
    mybatisplus
    0.67
     Мексичка
    0.67
     disambiguazione
    0.65
     مشين
    0.63
    msgTypes
    0.60
     ProtoMessage
    0.60
     nahilalakip
    0.59
    IsContent
    0.59
    ']){
    0.58
    Activations Density 1.803%

    No Known Activations