© 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. 1143
    Prev
    Next
    INDEX
    Explanations

    think through

    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
     تور
    0.39
     dor
    0.38
    дор
    0.38
    বুদ্ধ
    0.38
    ញ
    0.37
    ont
    0.37
     lc
    0.36
     d
    0.35
     aqu
    0.35
     nt
    0.35
    POSITIVE LOGITS
    Scale
    0.43
    ]})
    0.40
     foodstuffs
    0.39
    剂量
    0.38
    Thought
    0.38
    ochemical
    0.37
    сшта
    0.37
    SCALE
    0.37
    添付
    0.37
    소스
    0.37
    Activations Density 0.043%

    No Known Activations