© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42630
    Prev
    Next
    INDEX
    Explanations

    enctype="multipart/form-data"

    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_22_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
     truncation
    0.40
    ]._
    0.39
     subscription
    0.39
     subscribed
    0.38
     decreed
    0.38
     subscribing
    0.37
    ទី
    0.37
     subscript
    0.37
    規則
    0.37
    returned
    0.37
    POSITIVE LOGITS
    ﻄ
    0.39
     شی
    0.35
    кин
    0.33
     बिंदु
    0.33
     väik
    0.33
    凭借
    0.33
     uiteindelijk
    0.32
     مرات
    0.32
    Mobs
    0.32
     enorme
    0.32
    Activations Density 0.001%

    No Known Activations