© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46421
    Prev
    Next
    INDEX
    Explanations

    **Explanation:**a | b | cin

    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_22_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
    𝙍
    0.49
    ਥ
    0.43
     ਦਵਾਈ
    0.42
    графія
    0.42
     பெரும்பாலும்
    0.41
    Pharm
    0.40
     inequalities
    0.40
     সাধারণত
    0.40
    ografía
    0.39
     মূলত
    0.38
    POSITIVE LOGITS
    po
    0.41
     —
    0.40
    edown
    0.39
    ili
    0.39
    ahn
    0.38
    berry
    0.38
     D
    0.38
     don
    0.38
     Denmark
    0.38
    ainte
    0.38
    Activations Density 0.000%

    No Known Activations