© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5949
    Prev
    Next
    INDEX
    Explanations

    closing punctuation/brackets

    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_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     داعش
    0.42
     మాట్లాడుతూ
    0.41
    굵
    0.38
    靜
    0.38
     jakim
    0.37
    ங்களும்
    0.37
    大当たり
    0.37
    統領
    0.37
    hydroxy
    0.36
    ופי
    0.36
    POSITIVE LOGITS
     Zweiten
    0.41
    第二次
    0.38
     پک
    0.38
    atay
    0.36
     কন্
    0.35
     ഔ
    0.35
     Aun
    0.35
    esu
    0.35
     Second
    0.34
    Second
    0.34
    Activations Density 0.005%

    No Known Activations