© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175603
    Prev
    Next
    INDEX
    Explanations

    EPS and Share related financial metrics

    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_20_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
    нём
    0.46
    熵
    0.45
    
    0.44
     معاملہ
    0.42
     シート
    0.42
    Salam
    0.42
    swap
    0.41
     checkpoint
    0.41
    Produtos
    0.41
     दिरहम
    0.41
    POSITIVE LOGITS
     Femin
    0.45
     pompe
    0.44
     cui
    0.43
    匏
    0.43
     including
    0.42
    iscal
    0.42
    aved
    0.41
     multipl
    0.40
    伝統
    0.40
    ফস
    0.40
    Activations Density 0.000%

    No Known Activations