© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205470
    Prev
    Next
    INDEX
    Explanations

    dedicated / pure / specific

    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_20_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
     intimidating
    0.41
     контроля
    0.41
     hindrance
    0.40
     tinham
    0.39
     выполнения
    0.39
     intimidation
    0.39
    ಗು
    0.38
    }^{+}$,
    0.38
     తిన
    0.38
    damping
    0.38
    POSITIVE LOGITS
    人生
    0.39
     Pure
    0.38
     pure
    0.37
    Dedicated
    0.37
    Pure
    0.37
     Advers
    0.36
     retr
    0.36
    专门
    0.35
    参观
    0.35
    Viz
    0.35
    Activations Density 0.019%

    No Known Activations