© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9626
    Prev
    Next
    INDEX
    Explanations

    conectar, desigualdad, rival, punto

    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_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
    雅
    0.38
    üz
    0.37
     अवलंब
    0.37
    高级
    0.36
     интеллек
    0.36
     crossed
    0.36
     రాష్ట్ర
    0.36
    诉
    0.36
     منظ
    0.35
    ifa
    0.35
    POSITIVE LOGITS
     స
    0.40
    führung
    0.37
    Mathematical
    0.37
    సే
    0.36
     Mathematical
    0.36
     odk
    0.36
    amat
    0.36
     fierc
    0.36
    гез
    0.35
    conexion
    0.35
    Activations Density 0.057%

    No Known Activations