© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1079
    Prev
    Next
    INDEX
    Explanations

    customer service, interview, engineering

    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_39_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
    三星
    0.47
     samsung
    0.45
     삼성
    0.43
    삼성
    0.42
    mydb
    0.40
    至於
    0.39
     Dov
    0.38
    벽
    0.38
    াপ্ত
    0.38
    培训
    0.38
    POSITIVE LOGITS
     ・
    0.53
    ・
    0.51
    leqq
    0.48
    geqq
    0.45
    〜
    0.45
     〜
    0.43
    搬型
    0.42
     resin
    0.42
    処理
    0.41
    エル
    0.40
    Activations Density 0.040%

    No Known Activations