© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207613
    Prev
    Next
    INDEX
    Explanations

    Ada

    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_46_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
     antr
    0.39
     prices
    0.39
    connection
    0.36
     Price
    0.36
     Penh
    0.35
     Sovi
    0.35
    ြ
    0.35
    }_{+}\
    0.35
     मैनपुरी
    0.34
    interpreter
    0.34
    POSITIVE LOGITS
     Brendan
    0.43
    ナル
    0.41
    İL
    0.40
    bre
    0.39
     unen
    0.39
    רג
    0.38
     bre
    0.38
     Brend
    0.38
     Dys
    0.38
    fem
    0.38
    Activations Density 0.000%

    No Known Activations