© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33393
    Prev
    Next
    INDEX
    Explanations

    legal documents and proceedings

    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
     vitória
    0.51
     Wins
    0.50
     wins
    0.49
     побе
    0.49
     승
    0.49
     Litigation
    0.48
     thắng
    0.46
     derrota
    0.43
     Legal
    0.43
     litigation
    0.42
    POSITIVE LOGITS
    卒
    0.40
     दिल्‍ली
    0.39
    伖
    0.37
    versation
    0.37
    theorem
    0.36
    Cober
    0.36
    Atlant
    0.36
     surveillance
    0.35
    稳定
    0.35
    convergence
    0.35
    Activations Density 0.019%

    No Known Activations