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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9719
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation or SQL `where` clauses

    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
    蓑
    0.21
     durs
    0.20
    麸
    0.20
     Tabs
    0.19
     コス
    0.19
     dolgo
    0.19
     შორის
    0.19
    傚
    0.19
    vah
    0.19
    Okno
    0.19
    POSITIVE LOGITS
     sacrifices
    0.20
     JM
    0.20
     RV
    0.20
     }^{+}
    0.19
     principals
    0.19
    énagement
    0.18
     jej
    0.18
     CK
    0.18
    acker
    0.17
    kej
    0.17
    Activations Density 0.005%

    No Known Activations