© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48618
    Prev
    Next
    INDEX
    Explanations

    replace

    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_55_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
    aternal
    0.45
    省略
    0.43
    Hold
    0.40
    vigor
    0.39
    mek
    0.39
    HOLD
    0.38
     vigour
    0.37
    hold
    0.37
     持
    0.37
     mek
    0.37
    POSITIVE LOGITS
     replaced
    1.23
     replace
    1.21
     Replace
    1.15
     replaces
    1.13
     replacing
    1.11
    Replace
    1.11
    replaced
    1.06
     vervangen
    1.03
     заменить
    0.99
     Replacing
    0.98
    Activations Density 0.051%

    No Known Activations