© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 9940
    Prev
    Next
    INDEX
    Explanations

    `' OR '1'='1`

    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
    quettes
    0.28
     DEP
    0.27
    imde
    0.27
    issent
    0.26
    ANTED
    0.26
    gson
    0.26
    බ
    0.25
    ፨
    0.25
     excel
    0.25
     dando
    0.25
    POSITIVE LOGITS
    ynu
    0.28
    肌
    0.28
     肌
    0.28
    ີ່ມ
    0.28
    True
    0.27
     True
    0.26
     मुश्किल
    0.26
     ज़रूर
    0.26
     Frisch
    0.26
    アリング
    0.26
    Activations Density 0.002%

    No Known Activations