© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15634
    Prev
    Next
    INDEX
    Explanations

    text that describes details about the specs, production and restoration of automobiles

    oai_token-act-pair · gemini-2.0-flash

    vehicle-related terms

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

    vehicles

    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
    Negative Logits
     للمعارف
    -0.67
     CURIAM
    -0.65
     Orrell
    -0.61
    日閲覧
    -0.59
    mybatisplus
    -0.55
    Geografía
    -0.54
     transfieras
    -0.54
    Diweddarwch
    -0.52
    MessageState
    -0.52
    iastes
    -0.52
    POSITIVE LOGITS
    AsUp
    0.57
    Geplaatst
    0.57
    makeConstraints
    0.56
    +#+#
    0.54
    ]")]
    0.48
    τια
    0.48
     vehicles
    0.48
    )))),
    0.48
    ]))
    0.47
     azzurro
    0.47
    Activations Density 13.731%

    No Known Activations