© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126009
    Prev
    Next
    INDEX
    Explanations

    regularization techniques adding penalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    heat
    0.41
     heat
    0.41
     chaleur
    0.40
     প্রাকৃতিক
    0.39
    ὑ
    0.38
    坫
    0.37
    tag
    0.36
    circuit
    0.36
     eyelid
    0.36
    submission
    0.35
    POSITIVE LOGITS
     BatchNorm
    0.40
    忔
    0.40
    پيديا
    0.38
     方
    0.38
     Bloch
    0.37
     KC
    0.37
     yılları
    0.37
    ILTON
    0.37
    娴
    0.37
    꺽
    0.37
    Activations Density 0.003%

    No Known Activations