© 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. 167866
    Prev
    Next
    INDEX
    Explanations

    blocking access

    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
    Not in Any Lists

    No Comments

    Negative Logits
    备注
    0.32
    你也
    0.31
    inali
    0.29
     capitalismo
    0.29
     বৃদ্ধ
    0.29
    ಸರ್
    0.29
    蔘
    0.29
     sportive
    0.29
     Appearance
    0.28
    MORPH
    0.28
    POSITIVE LOGITS
     Nov
    0.32
     prox
    0.30
     textbook
    0.28
     skrz
    0.28
     wing
    0.28
     nov
    0.27
     fra
    0.27
    ຳ
    0.27
     hend
    0.26
     bł
    0.26
    Activations Density 0.006%

    No Known Activations