© 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. 6671
    Prev
    Next
    INDEX
    Explanations

    two sum

    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
    㶱
    0.22
    }+(\
    0.21
    itoti
    0.20
    ^{*}$
    0.20
    ሠራ
    0.20
     pazienti
    0.20
    壹章
    0.20
    getImageFolder
    0.20
     მთავ
    0.20
    BlockHash
    0.19
    POSITIVE LOGITS
     array
    0.29
    array
    0.25
    Array
    0.25
    阵
    0.25
    Arrays
    0.23
     Array
    0.23
    arrays
    0.21
     arrays
    0.21
     Arrays
    0.21
    陣
    0.20
    Activations Density 0.002%

    No Known Activations