© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247897
    Prev
    Next
    INDEX
    Explanations

    I

    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_56_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
    say
    0.48
     say
    0.44
     met
    0.44
     supposed
    0.44
     declined
    0.43
    汚
    0.43
     experienced
    0.43
    豐
    0.42
     upped
    0.42
     supposing
    0.41
    POSITIVE LOGITS
     genuinely
    0.45
     close
    0.43
     genu
    0.41
     rel
    0.41
    ――
    0.40
    close
    0.40
    čenje
    0.40
     relive
    0.39
     Won
    0.39
     نفسها
    0.38
    Activations Density 0.001%

    No Known Activations