© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214404
    Prev
    Next
    INDEX
    Explanations

    Hololive English / Latin suffixes

    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_5_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
    و
    1.27
     I
    1.21
    しまう
    1.03
    ों
    1.00
    기가
    0.98
    الی
    0.98
    एम
    0.97
    jima
    0.96
    도
    0.93
    activation
    0.93
    POSITIVE LOGITS
    ти
    1.44
    は
    1.30
    ta
    1.27
    to
    1.26
    ↵↵
    1.24
     is
    1.21
     n
    1.16
    на
    1.16
    ка
    1.15
    是
    1.14
    Activations Density 0.000%

    No Known Activations