© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3322
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $('#
    2.51
     со
    2.45
    $%
    2.40
     subdivision
    2.31
    来的
    2.24
    '_
    2.23
     cts
    2.22
    та
    2.15
     taxable
    2.12
    '/
    2.12
    POSITIVE LOGITS
    د
    2.83
    ف
    2.78
    ре
    2.73
    ح
    2.40
    েম্বর
    2.34
    etat
    2.34
    عت
    2.26
    િ
    2.20
    おり
    2.17
    عة
    2.13
    Activations Density 0.039%

    No Known Activations