© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198287
    Prev
    Next
    INDEX
    Explanations

    comma

    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_46_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
     βοη
    0.42
     मीन
    0.39
    ährung
    0.38
    lsch
    0.38
    ò
    0.37
    ്യൂ
    0.37
    ⁍
    0.36
    dR
    0.35
    ijek
    0.35
     kd
    0.35
    POSITIVE LOGITS
     hacker
    0.45
     hackers
    0.45
     Hackett
    0.43
    無線
    0.41
     Ironman
    0.41
     Interface
    0.41
     hacked
    0.41
     scoreboard
    0.39
    Interface
    0.39
     LO
    0.39
    Activations Density 0.001%

    No Known Activations