© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4451
    Prev
    Next
    INDEX
    Explanations

    gibberish or words in particular character encodings

    oai_token-act-pair · gemini-2.0-flash

    computer code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    prud
    -0.57
    عد
    -0.55
     asciug
    -0.51
     meurt
    -0.50
    pitched
    -0.50
     prostagland
    -0.49
    fach
    -0.49
    timation
    -0.48
     cleanliness
    -0.48
    ({});
    -0.48
    POSITIVE LOGITS
    SharedDtor
    0.76
     Савезне
    0.60
    contentLoaded
    0.57
    <bos>
    0.56
     ModelExpression
    0.56
    protoimpl
    0.54
     незавершена
    0.54
    ểm
    0.54
    MigrationBuilder
    0.53
    ebenarnya
    0.53
    Activations Density 0.217%

    No Known Activations