© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83974
    Prev
    Next
    INDEX
    Explanations

    purpose, superior, political

    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_29_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
     hata
    0.39
     diaper
    0.39
     covariance
    0.38
     amplitudes
    0.37
     waveform
    0.37
     grandpa
    0.37
    omass
    0.37
     ztr
    0.37
    }$.
    0.37
     geometry
    0.37
    POSITIVE LOGITS
     pháp
    0.42
    Eg
    0.41
     पूछ
    0.39
    Political
    0.39
     कानूनी
    0.38
    Emojis
    0.38
    ститу
    0.38
     lương
    0.38
    anteen
    0.37
     Eg
    0.37
    Activations Density 0.000%

    No Known Activations