© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158157
    Prev
    Next
    INDEX
    Explanations

    tightness/reversing

    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_50_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
     一
    0.48
    一本
    0.40
    AA
    0.39
    一周
    0.39
    一批
    0.38
     ਜ਼
    0.38
    そんな
    0.36
     Provinces
    0.36
    ByID
    0.36
    次的
    0.36
    POSITIVE LOGITS
    倒
    0.99
     tightness
    0.45
    紧
    0.44
    緊
    0.44
     tight
    0.43
     reversed
    0.40
     tighter
    0.40
     hoops
    0.39
     Tight
    0.39
     reversing
    0.39
    Activations Density 0.006%

    No Known Activations