© 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. 3848
    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
    𝑔
    2.27
    an
    2.06
    er
    1.94
    anthemum
    1.88
     gage
    1.88
    baiki
    1.88
    তা
    1.84
    Ǥ
    1.82
    뵌
    1.79
     notation
    1.76
    POSITIVE LOGITS
     ResponseEntity
    2.04
    𝓻
    1.93
    ال
    1.84
    m
    1.78
    ि
    1.76
    𝓼
    1.76
    𝙨
    1.75
    ments
    1.75
     meeste
    1.73
    \|$
    1.73
    Activations Density 0.036%

    No Known Activations