© 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. 253032
    Prev
    Next
    INDEX
    Explanations

    say Russian biological stems

    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
     m
    0.39
    コム
    0.38
    Leg
    0.37
     Polic
    0.37
     affluent
    0.36
     polig
    0.36
    จะได้
    0.36
     Holliday
    0.36
     Leg
    0.35
    DLC
    0.35
    POSITIVE LOGITS
     work
    0.59
     কাজ
    0.55
     works
    0.54
    清
    0.52
    工作
    0.52
     cle
    0.50
     trabalho
    0.49
     práce
    0.48
    งาน
    0.47
     работы
    0.47
    Activations Density 0.002%

    No Known Activations