© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23479
    Prev
    Next
    INDEX
    Explanations

    signs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     증
    1.66
    증
    1.52
    症
    1.28
     chứng
    1.17
    証
    1.04
     sert
    1.03
    证
    1.02
    證
    0.98
     أع
    0.98
    Chứng
    0.92
    POSITIVE LOGITS
     signs
    2.36
     Signs
    2.22
    Signs
    2.17
    signs
    2.17
     signos
    1.82
     signes
    1.80
     sign
    1.62
     signe
    1.51
     Sign
    1.50
     segni
    1.50
    Activations Density 0.030%

    No Known Activations