© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246618
    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_40_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
     Crete
    0.38
    performed
    0.38
     centrifugal
    0.37
     விழு
    0.37
    工夫
    0.37
    逆
    0.37
     ھ
    0.36
    டும்ப
    0.36
     metod
    0.36
    창
    0.36
    POSITIVE LOGITS
    thai
    0.41
    ári
    0.39
    依托
    0.39
     онлайн
    0.38
     fortæ
    0.38
    arelli
    0.36
    敘
    0.36
     послу
    0.36
    叙
    0.36
    경기
    0.34
    Activations Density 0.000%

    No Known Activations