© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152082
    Prev
    Next
    INDEX
    Explanations

    extreme intensity or severity

    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_23_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
    긔
    0.38
    োজিত
    0.35
     relay
    0.33
    ﾆ
    0.32
    nicheskij
    0.32
    ￱
    0.32
     minimized
    0.31
     आहोत
    0.31
    我们会
    0.31
     fielded
    0.31
    POSITIVE LOGITS
    ⵢ
    0.37
     Every
    0.36
     Đầu
    0.36
     samedi
    0.35
     गवा
    0.35
     Demir
    0.34
     complète
    0.33
     Brist
    0.33
     Been
    0.33
     Joker
    0.33
    Activations Density 0.025%

    No Known Activations