© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8428
    Prev
    Next
    INDEX
    Explanations

    the word "piece" along with related words about writing and coding, or edible things

    oai_token-act-pair · gemini-2.0-flash

    piece

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fjspx
    -0.51
    writeFieldEnd
    -0.50
    WhereInput
    -0.49
    ardown
    -0.48
    Diagnos
    -0.48
     ſeveral
    -0.48
    بوابة
    -0.47
     Curs
    -0.47
     समीक्षाएं
    -0.46
    ByVersion
    -0.46
    POSITIVE LOGITS
    httphttps
    0.62
    gdx
    0.56
     оригинала
    0.52
    ︎
    0.51
    peka
    0.51
    )))));
    0.50
    advertisement
    0.49
     préférences
    0.49
    MergeFrom
    0.48
    #+#
    0.48
    Activations Density 3.637%

    No Known Activations