© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31088
    Prev
    Next
    INDEX
    Explanations

    syllables followed by common endings

    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_31_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
     aro
    0.41
     لف
    0.40
    ereum
    0.38
    |_{
    0.36
     પૂ
    0.34
    ا۔
    0.34
     planning
    0.34
    део
    0.34
    盎
    0.34
    ोत
    0.33
    POSITIVE LOGITS
    сыпа
    0.40
    മ്പ്
    0.38
     सूर्या
    0.38
     বৃত্তি
    0.37
    porter
    0.36
    👠
    0.36
     თან
    0.36
     художника
    0.36
    FOL
    0.36
    имуще
    0.36
    Activations Density 0.001%

    No Known Activations