© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136791
    Prev
    Next
    INDEX
    Explanations

    python print("Hello, world!")

    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_37_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
     diplomats
    0.38
    🌀
    0.38
    რებული
    0.38
     Incredible
    0.38
     geometry
    0.37
     iteration
    0.36
     affinity
    0.36
     diplomatic
    0.36
     skates
    0.36
     médecine
    0.36
    POSITIVE LOGITS
     Lent
    0.40
    ణు
    0.39
    NAMES
    0.37
    鵬
    0.36
    polarized
    0.35
    ฟา
    0.35
     Logos
    0.35
    ניים
    0.34
     영
    0.34
    leftrightarrow
    0.34
    Activations Density 0.006%

    No Known Activations