© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30942
    Prev
    Next
    INDEX
    Explanations

    any further questions

    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
     покупки
    0.40
     আলোক
    0.39
     crossing
    0.38
    crossing
    0.38
    Crossing
    0.38
     crossings
    0.37
    叉
    0.37
     문서
    0.35
     판매
    0.35
     प्रकाश
    0.35
    POSITIVE LOGITS
    售后
    0.44
    बाब
    0.42
    ulador
    0.41
    arge
    0.40
     واس
    0.38
     Gone
    0.38
    }`}
    0.38
     серви
    0.37
     বর্ধ
    0.37
    ={'
    0.37
    Activations Density 0.000%

    No Known Activations