© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236933
    Prev
    Next
    INDEX
    Explanations

    Japanese and Korean verbs/particles

    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_32_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
    バード
    0.38
     absorption
    0.37
    地
    0.37
     llevando
    0.36
     Toen
    0.36
     swirls
    0.36
     cay
    0.35
     turtles
    0.35
     nails
    0.35
     cracking
    0.35
    POSITIVE LOGITS
     둘
    0.38
    소년
    0.38
     옳
    0.37
    されます
    0.36
    窑
    0.35
     Bucket
    0.35
     धरोहर
    0.34
    둘
    0.34
    ண்டும்
    0.34
     має
    0.34
    Activations Density 0.000%

    No Known Activations