© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116766
    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_27_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
     Jaaye
    0.37
     آئی
    0.37
    Opens
    0.37
     કરતી
    0.37
     বৎস
    0.37
    兔子
    0.35
    槨
    0.35
     Mant
    0.35
     saath
    0.35
    Rub
    0.35
    POSITIVE LOGITS
     offent
    0.42
     amend
    0.40
     linen
    0.40
    รร
    0.39
     lucro
    0.38
    changing
    0.37
    odb
    0.37
     flax
    0.37
     ভিতর
    0.36
     골
    0.35
    Activations Density 0.000%

    No Known Activations