© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5974
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to potential, progress, and advice, especially in the context of personal or athletic improvement

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     مرئيه
    -0.72
    PerformLayout
    -0.71
    ViewFeatures
    -0.64
    tonsoft
    -0.64
    MigrationBuilder
    -0.63
    addPreferredGap
    -0.63
    UnitTesting
    -0.63
    adpleegd
    -0.61
     typelib
    -0.60
    ValueStyle
    -0.59
    POSITIVE LOGITS
     ExecuteAsync
    0.48
    下载附件
    0.46
    脚注の使い方
    0.42
    ine
    0.42
     Pur
    0.41
    rabh
    0.41
    icz
    0.41
    ArgsConstructor
    0.41
    рд
    0.41
     ujednoznacz
    0.40
    Activations Density 0.708%

    No Known Activations