© 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. 5574
    Prev
    Next
    INDEX
    Explanations

    a wide variety of mostly short, common, relatively high-frequency words

    oai_token-act-pair · gemini-2.0-flash

    "this" in different languages

    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
    ArgsConstructor
    -0.68
    لينا
    -0.58
    例文帳に追加
    -0.54
     INTERESAR
    -0.51
    uxxxx
    -0.50
     utafitiHapana
    -0.49
    nila
    -0.46
    BufferException
    -0.46
    openqa
    -0.46
    xymatrix
    -0.45
    POSITIVE LOGITS
     this
    1.16
    this
    1.00
     dieser
    0.88
     này
    0.84
     این
    0.81
     hierdie
    0.79
     diese
    0.79
    この
    0.78
     이
    0.77
    This
    0.76
    Activations Density 0.893%

    No Known Activations