© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168126
    Prev
    Next
    INDEX
    Explanations

    built to last

    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_31_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
    ാണ
    0.38
     Insgesamt
    0.38
    ക്കണം
    0.37
    Diversity
    0.37
     আইনের
    0.36
    Ved
    0.36
    Здравствуйте
    0.36
    німа
    0.36
    rjust
    0.36
    㡴
    0.36
    POSITIVE LOGITS
     formada
    0.39
     costitu
    0.39
     Kec
    0.38
     Bitcoin
    0.38
     lifeline
    0.37
     固定
    0.37
     estrut
    0.36
     airline
    0.36
     Artificial
    0.36
     logistic
    0.36
    Activations Density 0.000%

    No Known Activations