© 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. 15004
    Prev
    Next
    INDEX
    Explanations

    code-related tokens concerning either translation between languages or quizzes

    oai_token-act-pair · gemini-2.0-flash

    coding and languages

    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
    omiast
    -0.51
     lalu
    -0.48
    Filmographie
    -0.45
    原始内容存档于
    -0.44
    seurs
    -0.43
     prefer
    -0.43
     `
    -0.42
     ver
    -0.42
    ])),
    -0.42
     виправивши
    -0.42
    POSITIVE LOGITS
    keyColumn
    0.56
    Билгалдахарш
    0.56
    blockList
    0.55
    fjspx
    0.55
    forKey
    0.54
    offsetof
    0.54
     intptr
    0.54
     怎样
    0.54
    esModule
    0.53
    BeginContext
    0.51
    Activations Density 1.827%

    No Known Activations