© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36956
    Prev
    Next
    INDEX
    Explanations

    heat and impact

    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_50_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
     ре
    0.48
     Snap
    0.47
     snap
    0.46
     Re
    0.43
    kien
    0.42
     RES
    0.41
     snaps
    0.41
     BODY
    0.41
    楇
    0.41
    xavier
    0.40
    POSITIVE LOGITS
    Hit
    0.54
    wand
    0.51
     Wand
    0.51
     wand
    0.48
     Hit
    0.48
     မှ
    0.41
     hit
    0.41
    ahit
    0.41
    held
    0.40
     Held
    0.39
    Activations Density 0.002%

    No Known Activations