© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208967
    Prev
    Next
    INDEX
    Explanations

    gentle/mild

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ила
    0.39
    ]");
    0.38
     ")";
    0.38
     DPR
    0.37
    ");//
    0.35
    ınca
    0.34
    薩
    0.34
    TaskList
    0.33
    =".
    0.33
    年会
    0.33
    POSITIVE LOGITS
     delicate
    2.75
     Delicate
    2.28
     delic
    2.22
     délic
    2.09
     delicately
    1.98
     delikat
    1.91
     delicacy
    1.90
     dainty
    1.23
     नाज
    1.16
    繊
    1.13
    Activations Density 0.018%

    No Known Activations