© 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-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141326
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_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
    ingle
    0.46
    ių
    0.45
     obligación
    0.44
    mathbf
    0.42
     para
    0.41
    ポルト
    0.40
     ​​
    0.39
     हार्मोन
    0.39
    erings
    0.39
     [])
    0.38
    POSITIVE LOGITS
    jev
    0.48
    تنا
    0.46
     up
    0.44
     Ezek
    0.44
    esha
    0.44
    玩的
    0.44
    屍
    0.44
     Первая
    0.43
     upas
    0.43
     knih
    0.43
    Activations Density 0.000%

    No Known Activations