© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10210
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Sar"

    oai_token-act-pair · gemini-2.0-flash

    the token "Sar"

    np_token-act-pair-logits · gpt-4o-mini

    Sar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     understood
    -0.54
     briefly
    -0.50
     tar
    -0.50
     كومونز
    -0.49
    انجليز
    -0.48
    исленность
    -0.47
     understanding
    -0.47
     brief
    -0.46
    styleUrls
    -0.46
    ーツ
    -0.46
    POSITIVE LOGITS
     itſelf
    0.69
    mybatisplus
    0.66
    StructEnd
    0.65
     houſe
    0.59
     againſt
    0.59
    ſelf
    0.57
     ſhe
    0.57
     propOrder
    0.56
    CppMethod
    0.56
    endphp
    0.56
    Activations Density 0.235%

    No Known Activations