© 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. 254049
    Prev
    Next
    INDEX
    Explanations

    friend

    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
     hard
    0.85
     heart
    0.71
    heart
    0.69
    hard
    0.66
    Heart
    0.66
    Hard
    0.64
     Heart
    0.59
     Hard
    0.57
     HEART
    0.56
    心
    0.52
    POSITIVE LOGITS
     friend
    2.59
     Friend
    2.16
    Friend
    1.90
    friend
    1.88
    友
    1.82
     amigo
    1.55
     vriend
    1.51
     FRIEND
    1.45
     amico
    1.43
     Freund
    1.34
    Activations Density 0.003%

    No Known Activations