© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15146
    Prev
    Next
    INDEX
    Explanations

    code snippets, URLs and bracketed phrases with pronouns

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     الحره
    -0.67
     AssemblyTitle
    -0.67
    PreferredItem
    -0.65
    脚注の使い方
    -0.63
     propOrder
    -0.61
    دانشنامهٔ
    -0.61
     незавершена
    -0.60
    osoba
    -0.59
    rrggbb
    -0.56
     XCTest
    -0.56
    POSITIVE LOGITS
    createStatement
    0.56
     WaitForSeconds
    0.55
    \{\\
    0.49
    pushFollow
    0.46
     ostavi
    0.46
    \}\\
    0.46
     Hall
    0.46
     onData
    0.45
    ">)</
    0.43
    closePath
    0.43
    Activations Density 3.419%

    No Known Activations