© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32209
    Prev
    Next
    INDEX
    Explanations

    5.`number`

    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_40_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
    জিওথেরাপি
    0.41
    牫
    0.37
    ^{*}$.
    0.37
     כן
    0.37
     realizacji
    0.36
     petition
    0.36
    🄴
    0.36
     नल
    0.35
     текста
    0.35
     পুনরুদ্ধার
    0.35
    POSITIVE LOGITS
    isma
    0.45
    By
    0.39
    ក្ខ
    0.37
     scarf
    0.36
    by
    0.35
    CG
    0.35
    Cached
    0.35
    BY
    0.35
    sets
    0.35
     obst
    0.34
    Activations Density 0.029%

    No Known Activations