© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4532
    Prev
    Next
    INDEX
    Explanations

    formal legal documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -1.30
    ########.
    -0.91
     utafitiHapana
    -0.75
    >//
    -0.67
    })));
    -0.64
    معلومات
    -0.63
    /**
    -0.63
     combineReducers
    -0.63
     internetowa
    -0.63
     ddelweddau
    -0.63
    POSITIVE LOGITS
    badlogic
    0.47
    انيف
    0.45
    KEYCODE
    0.43
     chère
    0.41
    ISSIPPI
    0.41
     proteine
    0.41
    ugou
    0.40
    oblotting
    0.40
     prawda
    0.39
    Holstein
    0.39
    Activations Density 41.987%

    No Known Activations