© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33156
    Prev
    Next
    INDEX
    Explanations

    drawing commands

    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
    𝗋
    0.44
    一方面
    0.42
     signalled
    0.40
    ẹ̀
    0.39
    phrine
    0.38
    烯
    0.38
     _{\
    0.38
     surprised
    0.37
    mfenced
    0.37
     signaled
    0.37
    POSITIVE LOGITS
     stratification
    0.43
     stratum
    0.40
    Danger
    0.37
    asibility
    0.37
    Adidas
    0.36
    osim
    0.36
     டை
    0.36
     Dread
    0.35
    企
    0.35
     ಮಧ್ಯ
    0.35
    Activations Density 0.005%

    No Known Activations