© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40629
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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_57_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
     ಹ
    0.43
     bestow
    0.42
     offended
    0.42
     jogs
    0.42
     предлага
    0.41
    Joh
    0.40
    Jog
    0.38
     Jing
    0.38
    became
    0.37
    蟾
    0.37
    POSITIVE LOGITS
     сх
    0.39
    뭅
    0.37
     Schumer
    0.36
    Burning
    0.36
     burning
    0.35
    زمانہ
    0.35
    தூ
    0.35
     unha
    0.34
    iez
    0.34
    AuthProvider
    0.34
    Activations Density 0.004%

    No Known Activations