© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9343
    Prev
    Next
    INDEX
    Explanations

    code snippets concerned with variable and object initialization in languages like JavaScript, C++, and potentially others, with a particular focus on initializer lists, constructors, and expression assignment.

    oai_token-act-pair · gemini-2.0-flash

    initializing/assignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Datuak
    -0.68
    ]--;
    -0.65
    DockStyle
    -0.63
     جغرافيا
    -0.56
     AspNetCore
    -0.54
     везе
    -0.52
     ✭✭
    -0.52
    PreferredItem
    -0.51
     وتسجيلات
    -0.50
    lioz
    -0.50
    POSITIVE LOGITS
     createSlice
    0.68
    ReusableCell
    0.63
    ]")]
    0.59
    typeorm
    0.57
    CardContent
    0.53
    awakeFromNib
    0.53
    ngOnInit
    0.50
     asti
    0.50
     chỉnh
    0.49
    SpringBootTest
    0.49
    Activations Density 2.083%

    No Known Activations