© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 180118
    Prev
    Next
    INDEX
    Explanations

    of

    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_50_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
     satta
    0.41
    ]}/
    0.39
     Ges
    0.37
    ترض
    0.36
     ges
    0.36
     크라운
    0.35
     CIS
    0.35
     ഇന്ത്യൻ
    0.35
     Maestro
    0.35
    氮
    0.35
    POSITIVE LOGITS
    ędzie
    0.40
    ABI
    0.39
     Tuj
    0.38
     Trib
    0.37
    abi
    0.36
     बु
    0.36
    acle
    0.36
    ưng
    0.35
    TextChanged
    0.35
     Tribute
    0.35
    Activations Density 0.001%

    No Known Activations