© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12470
    Prev
    Next
    INDEX
    Explanations

    phrases related to biographical information about a person, including birthdates, parents and family

    oai_token-act-pair · gemini-2.0-flash

    Biographies and personal histories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    </b>
    -0.45
     fecha
    -0.44
    </i>
    -0.43
     те
    -0.42
    </tbody>
    -0.41
     dòng
    -0.41
    gerät
    -0.40
    ネット
    -0.40
    ága
    -0.39
     net
    -0.39
    POSITIVE LOGITS
    StructEnd
    0.79
    djangoproject
    0.75
    oredCriteria
    0.74
    waitKey
    0.73
     للاسماء
    0.72
    endpush
    0.71
    adaptiveStyles
    0.68
    WebServlet
    0.68
     تضيفلها
    0.66
    таратура
    0.66
    Activations Density 6.446%

    No Known Activations