© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18897
    Prev
    Next
    INDEX
    Explanations

    api route definition

    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_34_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
     equil
    0.39
     वेबसाइट
    0.39
     संतुल
    0.39
     Wad
    0.39
     नक्
    0.38
    埒
    0.38
    愫
    0.38
     Уен
    0.37
    Pued
    0.37
    சின
    0.37
    POSITIVE LOGITS
     '/
    0.40
     නිෂ්පා
    0.39
    pathname
    0.38
     உற்பத்தி
    0.37
    off
    0.37
     "/
    0.36
     सप्लाई
    0.36
    ཥ
    0.35
    激安
    0.34
    outgoing
    0.34
    Activations Density 0.000%

    No Known Activations