© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181233
    Prev
    Next
    INDEX
    Explanations

    string literal names

    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_24_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
     grammaticality
    0.46
    alja
    0.45
     forment
    0.44
    ម៉
    0.41
    𝚢
    0.41
    asakan
    0.40
    PACE
    0.40
    жко
    0.40
    玽
    0.40
    亗
    0.40
    POSITIVE LOGITS
     has
    0.38
     prefers
    0.38
     النف
    0.38
     END
    0.37
     المنت
    0.37
     الع
    0.37
     reports
    0.37
    лении
    0.37
     ones
    0.36
     Pref
    0.36
    Activations Density 0.000%

    No Known Activations