© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90440
    Prev
    Next
    INDEX
    Explanations

    Subtraction case/choice

    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
    Negative Logits
    キ
    0.35
     aqua
    0.33
     domu
    0.33
    Aqua
    0.32
     Aqua
    0.32
     daughters
    0.31
    Dedicated
    0.31
     dusky
    0.31
    Aqu
    0.31
     handsets
    0.31
    POSITIVE LOGITS
     Multiply
    0.38
    䤃
    0.36
    嗥
    0.34
    浻
    0.33
     merav
    0.33
    筁
    0.33
     eredmény
    0.33
     ساله
    0.33
    Modify
    0.32
    ormány
    0.32
    Activations Density 0.005%

    No Known Activations